Reverse Engineering the Mind Consciously Acting Machines

and Accelerated Evolution

Visit the link below to download the full version of this book:

https://medipdf.com/product/reverse-engineering-the-mind-consciously-acting-mach
ines-and-accelerated-evolution/

Click Download Now

The only way to discover the limits of the possible
is to go beyond them into the impossible.
Sir Arthur C. Clarke
Preface

What we perceive as consciousness seems to be an anomaly, and so is intelligence. Earth

features a biodiversity of around 8.7 ∗ 10 ± 1.3 ∗ 10 SE (between ~7,400,000 and
~10,000,000) organisms, 1 from those just a few show rudimentary forms of both
consciousness and intelligence, and only one seems to be aware and discuss what it means to
exist. Although more than 1,000 exoplanets have been detected thitherto (latest estimations
predict around 1.7 ∗ 10 only in our galaxy), and 12 of them are probably habitable, there has
not been any indication that intelligent life apart from earth has emerged elsewhere. This may
be interpreted in many ways, whereby the most appealing ones for me are:
– Intelligence is an anomaly.
This assumption states that the probability for the evolution of human-like intelligence in
a species is infinitely small. No other species on earth seems to have developed it, which
can be considered as strong indication for the hypothesis that if extraterrestrial species
exist, they may not have developed it either. A similar thought experiment is about the
physical laws governing our universe. If universe parameters, such as the speed of light or
the strength of gravity, would have been allowed to take any value from 0 below infinity,
then the occurrence of the current set of parameters and parameter values governing the
very existence of the universe (and life) as we know it is infinitely low. Although I
personally do not hope and guess that this hypothesis is true, it has not yet been disproved
by scientific evidence.
– We are the first ones searching for intelligent life in our galaxy.
Considering the size of our galaxy and the time the universe already exists, it is very
likely that if intelligent life except from ours exists in whatever form, we will detect it
sooner or later, but: if we are not the only intelligent species in the universe it is, given the
almost 14 billion years that elapsed since the big bang, very unlikely that we are the first
ones having evolved intelligence, and in consequence the technology to communicate and
travel through space. More than half a century ago, even Enrico Fermi has faced the
paradox that considering the age of our universe, it should be very likely that intelligent
life has already emerged elsewhere. But where is it, then? This became widely known as
the Fermi-paradox.
– Other intelligent species have already discovered us, but do not (or cannot) show up for
some reason.
– No other species has solved the problem of how to produce exotic energy, which is, as to
current knowledge, required for travelling faster than light (to be exact, it is not travelling
faster than light, but bridging of distances by warping space-time). As no matter can
travel faster than light, it must be space-time that is moved through space-time. This can
theoretically be done by creating a warp-field around an area of space-time (and an object
like a spaceship within this area), which is bordered by a singularity in front of the object
and controlled expansion of space-time behind it. In theory this is possible, as has already
been shown with a special solution of Einstein's field equations in general relativity. This
solution states that the creation of an energy-impulse-tensor modifying the space-time
around a spacecraft in the sense that the distance between start- and endpoint can be

1 Tittensor Derek P. et al. (2011): How Many Species Are There on Earth and in the Ocean? [2013-
10-24]; URL: http://www.plosbiology.org/article/info%3Adoi%2F10.1371%2Fjournal.pbio.
1001127
VIII Preface

reduced is possible. However, for creating such a warp-field exotic matter, thus matter not
only not consisting of protons, neutrons or electrons, but additionally being of negative
energy density must be available2 – this may be a problem, as we have not even been able
to proof that it exists.
From a solely scientific point of view all of these and a lot more arguments are valid options,
but I will focus on the first one here. Mankind has always dreamed of immortality, which has,
amongst others, been one of the major reasons for why our species devised the concept of
religion. Our brain provides us with the abilities required to understand the universe, and the
more we understand about our role in the universe and life itself, the more transhumanistic
our views become. It may be not easy to accept that we will most likely take care of our
immortal soul ourselves in the not-so-distant future, but this is exactly what will happen.
Problems like starvation or over-population may be solved by leaving our bodily existence
behind, and hundreds of years-lasting journeys to exoplanets for colonization will not pose a
challenge for human minds transferred into the computers of spaceships. This is just a first
impression of what the future of mankind could be like. The ideas are countless, and history
taught us that advancement of science not always bears only good. Anyway, this work marks
the beginning of a journey – the journey towards consciously acting machines and artificially
accelerated human evolution.
Florian Neukart3

2 Alcubierre Miguel (1994): The warp drive: hyper-fast travel within general relativity; Classical
and.Quantum.Gravity 11:L73-L77, 1994
3 I am especially eager to note any copyrights of multimedia elements such as images and texts
used, and if possible to use graphics and text of my own. However, most of the time scientific
work is based on the work already done by others, which becomes apparent by having a look at
the number of publications cited within this elaboration. Every publishing scientist knows that one
challenge is that the more one reads and studies about a topic, the easier the boundaries of their
own ideas get blurred with those of others' ideas. Thus, if in this elaboration unmarked, but by
third party copyright protected images or a text are found, it was not possible for me to detect the
related copyright. In case of such an unintentional copyright violation I will remove the corres-
ponding picture or text element or will mark it with an appropriate copyright notice/citation of
sources indicated in the next version of the publication after a short notification.
Table of Contents

Preface ............................................................................................................................... VII

List of Figures ................................................................................................................. XVII
List of Tables .................................................................................................................... XXI
List of Algorithms .......................................................................................................... XXIII
List of Abbreviations ....................................................................................................... XXV

Introduction .......................................................................................................................... 1

Structure ............................................................................................................................... 3

1 Evolution’s most extraordinary achievement .......................................................7

1.1 Anatomy of the human brain....................................................................................... 7
1.1.1 Truncus cerebri ................................................................................................. 9
1.1.1.1 Cerebellum ................................................................................................ 9
1.1.1.2 Mesencephalon........................................................................................ 10
1.1.1.3 Pons ........................................................................................................ 11
1.1.1.4 Medulla oblongata ................................................................................... 12
1.1.2 Paleomammalian ............................................................................................ 12
1.1.2.1 Corpus amygdaloideum ........................................................................... 13
1.1.2.2 Hippocampus .......................................................................................... 14
1.1.2.3 Diencephalon .......................................................................................... 14
1.1.2.3.1 Hypothalamus .......................................................................... 15
1.1.2.3.2 Subthalamus ............................................................................ 16
1.1.2.3.3 Thalamus dorsalis .................................................................... 16
1.1.2.3.4 Pineal gland and Epithalamus .................................................. 16
1.1.2.4 Cingulate gyrus ....................................................................................... 16
1.1.3 Cortex and neocortex ...................................................................................... 17
1.1.3.1 Frontal lobe ............................................................................................. 18
1.1.3.2 Parietal lobe ............................................................................................ 18
1.1.3.3 Temporal lobe ......................................................................................... 19
1.1.3.4 Occipital lobe .......................................................................................... 20
1.2 Neural information transfer ....................................................................................... 21
1.3 Summary .................................................................................................................. 24

2 Pillars of artificial intelligence............................................................................. 25

2.1 Machine learning ...................................................................................................... 26
2.1.1 Supervised learning algorithms ....................................................................... 26
2.1.2 Unsupervised Learning Algorithms................................................................. 26
2.2 Computer Vision ...................................................................................................... 28
2.3 Logic and reasoning .................................................................................................. 30
2.4 Language and communication .................................................................................. 32
2.5 Agents and actions .................................................................................................... 34
X Table of Contents

2.5.1 Principles of the new agent-centered approach ................................................ 34

2.5.2 Multi-agent behavior ...................................................................................... 35
2.5.3 Multi-agent learning ....................................................................................... 36
2.6 Summary .................................................................................................................. 36

3 An outline of artificial neural networks .............................................................. 39

3.1 Definition ................................................................................................................. 39
3.2 Paradigms of computational intelligence ................................................................... 41
3.3 Neural networks ....................................................................................................... 42
3.3.1 Artificial neural networks ............................................................................... 42
3.3.1.1 Suitable problems .................................................................................... 44
3.3.1.2 Basic knowledge ..................................................................................... 45
3.3.1.2.1 Structure .................................................................................. 45
3.3.1.2.2 Bias ......................................................................................... 45
3.3.1.2.3 Gradient descent ...................................................................... 45
3.3.1.3 Activation functions ................................................................................ 46
3.3.1.3.1 Linear activation function ........................................................ 46
3.3.1.3.2 Sigmoid activation function ..................................................... 47
3.3.1.3.3 Hyperbolic tangent activation function ..................................... 47
3.3.1.3.4 Rectifier linear unit .................................................................. 48
3.3.1.3.5 Gaussian activation function .................................................... 49
3.3.1.4 Regularization ......................................................................................... 50
3.3.2 Types of artificial neural networks .................................................................. 51
3.3.2.1 Supervised and unsupervised learning ..................................................... 51
3.3.2.2 Feed-forward artificial neural network ..................................................... 51
3.3.2.3 Feed-forward artificial neural network with feedback connections ........... 51
3.3.2.4 Fully connected artificial neural network ................................................. 52
3.3.2.5 Basic artificial neural network structure ................................................... 52
3.3.2.6 Perceptron ............................................................................................... 53
3.3.2.6.1 Single layer perceptron ............................................................ 53
3.3.2.6.2 Multi layer perceptron.............................................................. 56
3.3.2.6.3 Spiking artificial neural networks ............................................. 58
3.3.2.7 Radial basis artificial neural network ....................................................... 59
3.3.2.8 Recurrent artificial neural network .......................................................... 59
3.3.2.8.1 Elman recurrent artificial neural network ................................. 60
3.3.2.8.2 Jordan recurrent artificial neural network ................................. 61
3.3.2.9 Fully connected artificial neural network ................................................. 62
3.3.2.9.1 Hopfield artificial neural network............................................. 64
3.3.2.9.2 Boltzmann Machine ................................................................. 66
3.3.2.9.3 Support vector machine............................................................ 71
3.3.2.9.4 Self-organizing feature map ..................................................... 72
3.3.2.9.5 Committee machines ................................................................ 74
3.3.3 Training and learning ...................................................................................... 77
3.3.3.1 Supervised and unsupervised training ...................................................... 77
3.3.3.2 (Root) mean squared error ....................................................................... 78
3.3.3.3 Estimators ............................................................................................... 79
3.3.3.4 Hebb's learning rule ................................................................................. 79
Table of Contents XI

3.3.3.5 Delta rule................................................................................................. 80

3.3.3.6 Propagation learning ................................................................................ 81
3.3.3.6.1 Back propagation training ........................................................ 82
3.3.3.6.2 Manhattan update rule training ................................................. 86
3.3.3.6.3 Resilient propagation ............................................................... 87
3.3.3.7 Genetic learning (NeuroEvolution) .......................................................... 90
3.3.3.7.1 Evolutionary search of connection weights............................... 93
3.3.3.7.2 Evolutionary search of architectures ......................................... 93
3.3.3.7.3 Evolutionary search of learning rules ....................................... 94
3.3.3.8 Simulated annealing ................................................................................ 94
3.3.3.9 NeuroEvolution of augmenting topologies (NEAT) ................................. 96
3.3.4 Stability-plasticity dilemma ............................................................................ 99
3.4 Summary ................................................................................................................ 100

4 Advanced artificial perception and pattern recognition .................................. 103

4.1 Convolutional artificial neural networks ................................................................. 104
4.1.1 Data representation ....................................................................................... 105
4.1.2 Structure ....................................................................................................... 106
4.1.2.1 Convolutional layers .............................................................................. 107
4.1.2.2 Different ways of perception and processing.......................................... 111
4.1.2.3 Maxpooling/ downsampling layers ........................................................ 112
4.1.2.4 Feature maps ......................................................................................... 112
4.1.2.5 Fully connected layers ........................................................................... 114
4.1.2.6 Number of neurons ................................................................................ 114
4.1.3 Training ........................................................................................................ 114
4.2 Deep belief artificial neural network ....................................................................... 118
4.2.1 Stacking together RBMs ............................................................................... 122
4.2.2 Training ........................................................................................................ 122
4.3 Cortical artificial neural network ............................................................................ 123
4.3.1 Structure ....................................................................................................... 125
4.3.1.1 Cortices ................................................................................................. 127
4.3.1.2 Number of neurons ................................................................................ 127
4.3.1.3 Synapses ............................................................................................... 128
4.3.2 A generic cortical artificial neural network ................................................... 128
4.3.3 Purpose......................................................................................................... 130
4.3.4 Evolution and weight initialization ............................................................... 131
4.4 SHOCID recurrent artificial neural network ............................................................ 134
4.4.1 Structure ....................................................................................................... 134
4.4.1.1 Recurrent layer one ............................................................................... 135
4.4.1.2 Recurrent layer two ............................................................................... 136
4.4.1.3 Number of neurons ................................................................................ 137
4.4.1.4 Synapses ............................................................................................... 138
4.4.2 Purpose......................................................................................................... 138
4.4.3 Evolution and weight initialization ............................................................... 139
4.5 Summary ................................................................................................................ 141
XII Table of Contents

5 Advanced nature-inspired evolution and learning strategies .......................... 143

5.1 Transgenetic NeuroEvolution ................................................................................. 143
5.1.1 Fundamentals ............................................................................................... 144
5.1.2 Host genetic material .................................................................................... 145
5.1.3 Endosymbiont............................................................................................... 146
5.1.4 Algorithm ..................................................................................................... 146
5.1.5 Horizontal (endosymbiotic) gene (sequence) transfer .................................... 147
5.1.5.1 Weight plasmid ..................................................................................... 148
5.1.5.2 Structure plasmid................................................................................... 148
5.1.6 Transposon mutation .................................................................................... 149
5.1.6.1 Jump and swap transposon .................................................................... 149
5.1.6.2 Erase and jump transposon .................................................................... 150
5.1.7 Usage ........................................................................................................... 150
5.2 Artificial immune system-inspired NeuroEvolution ................................................ 150
5.2.1 Fundamentals ............................................................................................... 151
5.2.2 Clonal selection and somatic hypermutation ................................................. 152
5.2.3 Danger theory, virus attack and hyperrecombination ..................................... 155
5.2.4 Negative selection ........................................................................................ 158
5.2.5 Overall algorithm.......................................................................................... 160
5.2.6 Causality ...................................................................................................... 161
5.2.7 Usage ........................................................................................................... 162
5.3 Structural evolution ................................................................................................ 162
5.3.1 Fundamentals ............................................................................................... 162
5.3.2 Algorithm ..................................................................................................... 163
5.3.3 Generic determination of artificial neural network quality............................. 165
5.3.4 Parameterization ........................................................................................... 167
5.3.5 Usage ........................................................................................................... 167
5.4 Summary ................................................................................................................ 167

6 Autonomously acting cars and predicting market

behaviour: some application scenarios for ANNs ............................................ 169
6.1 Analysis and knowledge ......................................................................................... 169
6.1.1 Supervised and unsupervised functions ......................................................... 171
6.1.2 Classification ................................................................................................ 171
6.1.3 Regression .................................................................................................... 172
6.1.4 Clustering ..................................................................................................... 172
6.1.5 Attribute importance ..................................................................................... 173
6.1.6 Association ................................................................................................... 173
6.1.7 Interesting knowledge ................................................................................... 173
6.1.8 Accurate knowledge ..................................................................................... 174
6.1.9 Interpretable knowledge................................................................................ 174
6.1.10 Intelligent processing .................................................................................... 174
6.1.11 Efficient processing ...................................................................................... 174
6.2 Autonomously acting cars ....................................................................................... 175
6.2.1 V2X-communication .................................................................................... 176
6.2.2 Massively equip car with processing power and AI-algorithms ..................... 176
Table of Contents XIII

6.2.3 Artificial intelligence and environment sensing ............................................. 176

6.2.3.1 Cameras and how AI is applied to related data ....................................... 177
6.2.3.2 RADAR and how AI is applied to related data ....................................... 177
6.2.3.3 LiDAR and how AI is applied to related data......................................... 178
6.2.3.4 Additional sensors and how AI is applied to related data ....................... 178
6.2.3.5 GPS and how AI is applied to related data ............................................. 179
6.2.3.6 Microphones and how AI is applied to related data ................................ 179
6.2.3.7 Autonomously acting car’s brain – the domain controller ...................... 179
6.3 Summary ................................................................................................................ 180

7 An outline of quantum mechanics ..................................................................... 181

7.1 Quantum systems in general ................................................................................... 181
7.1.1 Quantum theory ............................................................................................ 182
7.1.1.1 Quantum states ...................................................................................... 182
7.1.1.2 Observables ........................................................................................... 183
7.1.1.3 Quantum measurements ........................................................................ 184
7.1.1.4 Quantum dynamics ................................................................................ 185
7.1.2 Quantum operators ....................................................................................... 186
7.1.3 Quantum physical effects .............................................................................. 190
7.1.3.1 Quantum interference ............................................................................ 190
7.1.3.2 Quantum linear superposition ................................................................ 192
7.1.3.3 Quantum entanglement .......................................................................... 193
7.2 The unitary evolution U .......................................................................................... 195
7.3 The state vector reduction R ................................................................................... 198
7.4 Summary ................................................................................................................ 219

8 Quantum physics and the biological brain ....................................................... 221

8.1 Difficulties with U in the macroscopic world .......................................................... 222
8.2 The Hameroff-Penrose model of orchestrated objective reduction ........................... 224
8.2.1 The idea ........................................................................................................ 224
8.2.2 Microtubules ................................................................................................ 225
8.3 Further models ........................................................................................................ 228
8.4 Summary ................................................................................................................ 229

9 Matter and consciousness .................................................................................. 231

9.1 Qualia ..................................................................................................................... 231
9.2 Materialism ............................................................................................................ 232
9.2.1 Eliminative materialism ................................................................................ 233
9.2.2 Noneliminative materialism .......................................................................... 233
9.3 Functionalism ......................................................................................................... 233
9.3.1 The problem of absent or inverted qualia ...................................................... 234
9.3.2 The Chinese Room argument ........................................................................ 234
9.3.3 The knowledge argument .............................................................................. 235
XIV Table of Contents

9.4 The Identity Theory ................................................................................................ 235

9.5 Summary ................................................................................................................ 236

10 Reverse engineering the mind ........................................................................... 237

10.1 Theory of mind ....................................................................................................... 237
10.2 Quantum linear superposition in artificial brains ..................................................... 238
10.3 Self-organization .................................................................................................... 241
10.3.1 Structure and system ..................................................................................... 242
10.3.1.1 Conservative structure ........................................................................... 242
10.3.1.2 Dissipative structure .............................................................................. 243
10.3.2 Self-organization in computational intelligence ............................................ 243
10.3.2.1 Self-organized learning.......................................................................... 246
10.3.2.2 Learning with respect to self-organization ............................................. 246
10.3.2.2.1Competitive learning .............................................................. 248
10.3.2.2.2Competitive learning in artificial neural networks .................. 249
10.3.2.3 Adaptive Resonance Theory .................................................................. 251
10.3.3 The transition to the human brain .................................................................. 254
10.3.3.1 Laterally interconnected synergetically self-organizing maps ................ 257
10.3.3.2 The pruning neocortex ........................................................................... 259
10.3.3.2.1Incremental pruning ............................................................... 260
10.3.3.2.2Selective pruning ................................................................... 260
10.3.3.2.3Pruning and quantum artificial neural networks...................... 260
10.3.4 Arguments for self-organization in artificial neural systems .......................... 261
10.4 Mechanisms apart from self-organization ............................................................... 261
10.4.1 Leader .......................................................................................................... 262
10.4.2 Blueprint ...................................................................................................... 262
10.4.3 Recipe .......................................................................................................... 262
10.4.4 Template ...................................................................................................... 262
10.5 Quantum physics and the artificial brain ................................................................. 263
10.5.1 Quantum artificial neural network................................................................. 263
10.5.1.1 Structure................................................................................................ 264
10.5.1.2 Quantum bits ......................................................................................... 266
10.5.1.3 Superposition ........................................................................................ 266
10.5.1.3.1Superposition of dendrites ...................................................... 266
10.5.1.3.2Superposition of neurons ........................................................ 267
10.5.1.3.3Superposition of the quantum artificial neural network........... 267
10.5.1.4 Entanglement ........................................................................................ 268
10.5.1.5 Interference ........................................................................................... 275
10.5.1.6 Processing ............................................................................................. 277
10.5.1.6.1Entanglement ......................................................................... 278
10.5.1.6.2Quantum parallelism .............................................................. 279
10.5.1.6.3From basic operators to the quantum transfer function ........... 279
10.5.1.6.4Reduction of and information about the quantum
perceptron equations .............................................................. 284
10.5.1.6.5Normalization ........................................................................ 289
10.5.1.7 Measurement ......................................................................................... 290
Table of Contents XV

10.5.1.7.1Quantum artificial neural network configuration search

function ................................................................................. 290
10.5.1.7.2Example processing ............................................................... 291
10.5.1.8 Envisaged implementations of a quantum artificial neural network ........ 295
10.5.1.8.1Adiabatic quantum annealing ................................................. 298
10.5.1.8.2Nuclear magnetic resonance ................................................... 298
10.5.1.8.3Others .................................................................................... 299
10.6 The artificial neocortex ........................................................................................... 299
10.6.1 Knowledge and data ..................................................................................... 301
10.6.1.1 Knowledge representation ..................................................................... 302
10.6.1.2 Declarative knowledge representation ................................................... 302
10.6.1.2.1Semantic networks ................................................................. 303
10.6.1.2.2Object-attribute-value-triplet .................................................. 304
10.6.1.2.3Frames ................................................................................... 305
10.6.2 Context recognition and hierarchical learning ............................................... 309
10.6.2.1 Definition of context-sensitive information ............................................ 310
10.6.2.2 Information Clustering .......................................................................... 311
10.6.2.3 Context analysis .................................................................................... 312
10.6.2.4 Hierarchical learning ............................................................................. 313
10.6.2.5 Interpreting the context .......................................................................... 315
10.6.2.6 Hidden Markov models and conceptual hierarchies in the neocortex...... 317
10.6.3 Implementation............................................................................................. 325
10.6.3.1 Acquisition of basic knowledge ............................................................. 328
10.6.3.2 Encoding the acquired knowledge into pattern recognizers .................... 329
10.6.3.3 Access to knowledge and how search engines are similar to the brain .... 333
10.6.3.4 Language processing and understanding ................................................ 337
10.6.3.5 Quantum pattern recognizers ................................................................. 343
10.6.3.6 Real world input and new experiences ................................................... 345
10.6.3.7 Automatic information interconnection.................................................. 346
10.6.4 A superior goal ............................................................................................. 346
10.7 A distributed mind .................................................................................................. 347
10.7.1 Non-invasive transducers .............................................................................. 349
10.7.2 Semi-invasive, invasive transducers and the neural grid ................................ 350
10.7.3 Signal processing .......................................................................................... 350
10.7.3.1 Pre-processing ...................................................................................... 351
10.7.3.2 Feature extraction .................................................................................. 351
10.7.3.3 Detection and classification ................................................................... 351
10.7.4 BCI requirements for the distributed mind .................................................... 352
10.8 Summary ................................................................................................................ 353

11 Conclusion .......................................................................................................... 355

Glossary – computational intelligence .................................................................. 357

Glossary – quantum physics .................................................................................. 365

Bibliography ........................................................................................................... 371

List of Figures

Figure 1 - Human brain.......................................................................................................... 8

Figure 2 - Triune brain ........................................................................................................... 8
Figure 3 – Truncus cerebri ..................................................................................................... 9
Figure 4 - Cerebellum .......................................................................................................... 10
Figure 5 - Mesencephalon.................................................................................................... 11
Figure 6 - Pons .................................................................................................................... 11
Figure 7 - Medulla oblongata ............................................................................................... 12
Figure 8 - Paleomammalian ................................................................................................. 13
Figure 9 - Corpus amygdaloideum ....................................................................................... 13
Figure 10 - Hippocampus .................................................................................................... 14
Figure 11 - Diencephalon .................................................................................................... 15
Figure 12 - Hypothalamus ................................................................................................... 16
Figure 13 - Frontal lobe ....................................................................................................... 18
Figure 14 - Parietal lobe ...................................................................................................... 19
Figure 15 – Temporal lobe ................................................................................................... 20
Figure 16 - Occipital lobe .................................................................................................... 21
Figure 17 - Neuron .............................................................................................................. 21
Figure 18 - Neuron types ..................................................................................................... 22
Figure 19 - Action potential ................................................................................................. 23
Figure 20 - McCulloch & Pitts neuron model....................................................................... 43
Figure 21 - Representative processing model ....................................................................... 43
Figure 22 - Linear activation................................................................................................ 46
Figure 23 - Sigmoid activation............................................................................................. 47
Figure 24 - Tangens hyperbolicus activation ........................................................................ 48
Figure 25 - ReLu activation ................................................................................................. 48
Figure 26 - Gauss activation ................................................................................................ 49
Figure 27 - Simple artificial neural network structure .......................................................... 52
Figure 28 – Single layer perceptron ..................................................................................... 54
Figure 29 – OR operator ...................................................................................................... 56
Figure 30 – AND operator ................................................................................................... 56
Figure 31 – XOR operator ................................................................................................... 56
Figure 32 – Multi layer perceptron....................................................................................... 57
Figure 33 - Elman artificial neural network.......................................................................... 61
Figure 34 - Jordan artificial neural network ......................................................................... 62
XVIII List of Figures

Figure 35 - Hopfield artificial neural network ...................................................................... 65

Figure 36 - Boltzmann machine ........................................................................................... 67
Figure 37 - Restricted Boltzmann machine .......................................................................... 68
Figure 38 – Self organizing feature map .............................................................................. 73
Figure 39 - Committee machine ........................................................................................... 75
Figure 40 - Hebb's rule ........................................................................................................ 80
Figure 41 - Delta rule........................................................................................................... 81
Figure 42 – NeuroEvolution of augmenting topologies mutation ......................................... 97
Figure 43 – NeuroEvolution of augmenting topologies recombination of different
topologies ....................................................................................................... 98
Figure 44 - 4-dimensional tensor ....................................................................................... 105
Figure 45 – CNN sparse interconnectivity ......................................................................... 106
Figure 46 - CNN architecture............................................................................................. 107
Figure 47 – Convolution .................................................................................................... 107
Figure 48 – ( ) ................................................................................................................ 108
Figure 49 – ( ) ................................................................................................................ 109
Figure 50 – ( ) ................................................................................................................ 109
Figure 51 – reflected .................................................................................................... 110
Figure 52 – reflected and shifted .................................................................................. 110
Figure 53 – Convolution of and − ......................................................................... 110
Figure 54 – Activation map ............................................................................................... 112
Figure 55 – Downsampled activation map ......................................................................... 112
Figure 56 – Convolution calculation .................................................................................. 113
Figure 57 - Featuremap generation .................................................................................... 115
Figure 58 - Simple ANN .................................................................................................... 119
Figure 59 – Causal brain influence types ........................................................................... 124
Figure 60 – Pre-cortical artificial neural network structure ................................................. 125
Figure 61 – Cortical artificial neural network structure ...................................................... 126
Figure 62 – Cortical artificial neural network structure ...................................................... 129
Figure 63 – SHOCID recurrent artificial neural network single hidden layer ...................... 135
Figure 64 – SHOCID recurrent artificial neural network multi hidden layer ....................... 137
Figure 65 - Transgenetic NeuroEvolution .......................................................................... 145
Figure 66 - Bloch sphere .................................................................................................... 196
Figure 67 - Euler's formula ................................................................................................ 198
Figure 68 - Photon and half-silvered mirror ....................................................................... 202
Figure 69 - Photon, half-silvered and fully-silvered mirrors ............................................... 202
List of Figures XIX

Figure 70 - Infinite potential step ....................................................................................... 204

Figure 71 - Finite potential step ......................................................................................... 207
Figure 72 - Particle lacks energy ........................................................................................ 211
Figure 73 - Potential barrier ............................................................................................... 211
Figure 74 - Potential barrier - forces .................................................................................. 212
Figure 75 - ART1 Structure ............................................................................................... 252
Figure 76 - Monkey striate cortex recording, ..................................................................... 255
Figure 77 - Quantum artificial neural network ................................................................... 265
Figure 78 – Quantum teleportation network unit ................................................................ 270
Figure 79 - cNOT from H and V ........................................................................................ 281
Figure 80 - Toffoli gate with controlled V ......................................................................... 281
Figure 81 - Toffoli-gate with complex conjugate transpose V ............................................ 282
Figure 82 - Quantum addition ............................................................................................ 283
Figure 83 – Quantum artificial neural network calculations ............................................... 286
Figure 84 - Quantum single layer perceptron diagram ........................................................ 287
Figure 85 - Quantum multi layer perceptron diagram ......................................................... 288
Figure 86 - Reverse the calculation bits ............................................................................. 288
Figure 87 - Rotation towards | ....................................................................................... 293
Figure 88 - Quantum Hopfield artificial neural network ..................................................... 296
Figure 89 - Quantum Boltzmann machine .......................................................................... 297
Figure 90 – Semantic network ........................................................................................... 303
Figure 91 – Representation of n-digit predicates ................................................................ 304
Figure 92 – O-A-V-triplet .................................................................................................. 305
Figure 93 - Markov chain weather prediction ..................................................................... 319
Figure 94 - Markov chain interpretation of speech signals ................................................. 319
Figure 95 - Markov chain .................................................................................................. 320
Figure 96 - Hidden Markov model ..................................................................................... 321
Figure 97 - Hidden Markov model weather observations ................................................... 322
Figure 98 - Hierarchically hidden Markov model ............................................................... 324
Figure 99 - Pattern presented to multiple pattern recognizers ............................................. 326
Figure 100 - Hierarchical pattern processing ...................................................................... 327
Figure 101 - Binary decision tree ....................................................................................... 331
Figure 102 - Bottom-up ANN tree ..................................................................................... 332
Figure 103 - Cumulative activation .................................................................................... 333
Figure 104 - Viterbi example ............................................................................................. 338
Figure 105 - Variable explanation ...................................................................................... 340