Name - Sonali Garad

Urn no- 2021-M-24081991

Subject – Reinforcement Learning
ARTIFICIAL INTELLIGENCE WITH PYTHON

 Python is among the most widely used programming languages that developers use
in the present. Guido Van Rossum created it in 1991, and since its beginning, it has
been among the most popular languages alongside C++, Java, and others.
 Python is also considered to be a general-purpose programming language, which
means that it is able to be utilized across technology and domains.
 Python also comes with a dynamic type system and automatic memory management
that support various programming techniques, such as object-oriented, functional,
imperative, and procedural, to mention just only a few.
 Python is accessible for every Operating system and has an open-source offering
called CPython that is gaining huge popularity.
 ARTIFICIAL INTELLIGENCE AND PYTHON: WHY?

 Python comes with Prebuilt Libraries such as Numpy to perform scientific

calculations, Scipy for advanced computing, and Pybrain for machine learning
(Python Machine Learning), making it among the top languages for AI.
 Python developers all over the globe offer extensive support and assistance
through tutorials and forums, helping the programmer much easier than another
popular language.
 Python is platform-independent and therefore is among the most adaptable and
well-known options for various platforms and technologies, with minimal
modifications to the basics of coding.
 Python has the greatest flexibility among other programs, with the option of
choosing among OOPs method and scripting. Additionally, you can use the IDE
to search for all codes and be a blessing to developers struggling with different
algorithms.
PYTHON LIBRARIES FOR GENERAL ARTIFICIAL INTELLIGENCE

 AIMA - Python algorithm implementation comes directly from Russell as

well as Norvig's "Artificial intelligence: A Modern Methodology. "
 pyDatalog - Logic Programming engine in Python

 SimpleAI - Python implementation of various artificial intelligence

algorithms explained in "Artificial Intelligence, a Modern Approach ". Its
primary goal is to provide intuitive, well-documented, and tested libraries.
 EasyAI - A simple Python engine that allows two players to play games
using AI (Negamax and transposition tables for Game-solving).
 PYTHON FOR MACHINE LANGUAGE (ML)
 PyBrain - is an easy yet flexible algorithm to perform Machine Learning tasks. It
also functions as an extensible Machine Learning Library for Python that
provides a range of predefined environments for testing and evaluating
algorithms.
 PyML - A bidirectional framework developed in Python concentrates on SVMs
and other kernel-based approaches. It's accessible on Linux and Mac OS X.
 Scikit-learn - can be described as an effective instrument for data analysis
making use of Python. This is a completely free and open-source library. It is the
most widely used general-purpose machine learning library.
 MDP - Toolkit A different Python Data Processing Framework that is easily
extended contains a variety of unsupervised and supervised learning algorithms
and other computing units for data analysis that could be combined to create
sequences of data processing and more intricate feed-forward networks.
ARTIFICIAL NEURONS

 Artificial neuron also known as perceptron is the basic unit of the neural network.
In simple terms, it is a mathematical function based on a model of biological
neurons. It can also be seen as a simple logic gate with binary outputs. They are
sometimes also called perceptrons.
 Each artificial neuron has the following main functions:

 Takes inputs from the input layer

 Weighs them separately and sums them up

 Pass this sum through a nonlinear function to produce output.

 BIOLOGICAL NEURONS
 Neurons are the basic functional units of the nervous system, and they generate
electrical signals called action potentials, which allows them to quickly transmit
information over long distances.
Almost all the neurons have three basic functions essential for the normal
functioning of all the cells in the body.
 These are to:
1. Receive signals (or information) from outside.
2. Process the incoming signals and determine whether or not the information
should be passed along.
3. Communicate signals to target cells which might be other neurons or muscles
or glands.
 Now let us understand the basic parts of a neuron to get a deeper insight into how
they actually work…
• ACTIVATION FUNCTIONS IN NEURAL NETWORKS

 Linear or Identity Activation Function.

 Non-linear Activation Function.

 Sigmoid or Logistic Activation Function.

 Tanh or hyperbolic tangent Activation Function.

 ReLU (Rectified Linear Unit) Activation Function.

 Leaky ReLU.
SOFTMAX ACTIVATION FUNCTION WITH PYTHON

 Softmax is a mathematical function that converts a vector of numbers into a

vector of probabilities, where the probabilities of each value are proportional to
the relative scale of each value in the vector.
 The most common use of the softmax function in applied machine learning is in
its use as an activation function in a neural network model. Specifically, the
network is configured to output N values, one for each class in the classification
task, and the softmax function is used to normalize the outputs, converting them
from weighted sum values into probabilities that sum to one. Each value in the
output of the softmax function is interpreted as the probability of membership for
each class.
 In this tutorial, you will discover the softmax activation function used in neural
network models.
WHAT IS A LOSS FUNCTION AND LOSS?

 In the context of an optimization algorithm, the function used to evaluate a

candidate solution (i.e. a set of weights) is referred to as the objective function.
 We may seek to maximize or minimize the objective function, meaning that we
are searching for a candidate solution that has the highest or lowest score
respectively.
 Typically, with neural networks, we seek to minimize the error. As such, the
objective function is often referred to as a cost function or a loss function and the
value calculated by the loss function is referred to as simply “loss.”
 The function we want to minimize or maximize is called the objective function or
criterion. When we are minimizing it, we may also call it the cost function, loss
function, or error function.
 ADVANTAGES OF ARTIFICIAL NEURAL NETWORK
 Parallel processing capability:

 Artificial neural networks have a numerical value that can perform more than one
task simultaneously.
 Storing data on the entire network:

 Data that is used in traditional programming is stored on the whole network, not
on a database. The disappearance of a couple of pieces of data in one place
doesn't prevent the network from working.
 Capability to work with incomplete knowledge:

 After ANN training, the information may produce output even with inadequate
data. The loss of performance here relies upon the significance of missing data.
 Having a memory distribution:

 For ANN is to be able to adapt, it is important to determine the examples and to

encourage the network according to the desired output by demonstrating these
examples to the network.
DISADVANTAGES OF ARTIFICIAL NEURAL NETWORK

 Assurance of proper network structure:

 There is no particular guideline for determining the structure of artificial neural networks. The appropriate
network structure is accomplished through experience, trial, and error.
 Unrecognized behavior of the network:
 It is the most significant issue of ANN. When ANN produces a testing solution, it does not provide insight
concerning why and how. It decreases trust in the network.
 Hardware dependence:
 Artificial neural networks need processors with parallel processing power, as per their structure. Therefore,
the realization of the equipment is dependent.
 Difficulty of showing the issue to the network:
 ANNs can work with numerical data. Problems must be converted into numerical values before being
introduced to ANN. The presentation mechanism to be resolved here will directly impact the performance
of the network. It relies on the user's abilities.
 TYPES OF ARTIFICIAL NEURAL NETWORK
 There are various types of Artificial Neural Networks (ANN) depending upon the human brain neuron
and network functions, an artificial neural network similarly performs tasks. The majority of the artificial
neural networks will have some similarities with a more complex biological partner and are very
effective at their expected tasks. For example, segmentation or classification.
 Feedback ANN:
 In this type of ANN, the output returns into the network to accomplish the best-evolved results
internally. As per the University of Massachusetts, Lowell Centre for Atmospheric Research. The
feedback networks feed information back into itself and are well suited to solve optimization issues. The
Internal system error corrections utilize feedback ANNs.
 Prerequisite
 No specific expertise is needed as a prerequisite before starting this tutorial.
 Audience
 Our Artificial Neural Network Tutorial is developed for beginners as well as professionals, to help them
understand the basic concept of ANNs.
DEEP LEARNING ALGORITHMS
 Convolutional Neural Networks (CNNs)
 Long Short Term Memory Networks (LSTMs)

 Recurrent Neural Networks (RNNs)

 Generative Adversarial Networks (GANs)

 Radial Basis Function Networks (RBFNs)

 Multilayer Perceptrons (MLPs)

 Self Organizing Maps (SOMs)

DATA SCIENCE COMPONENTS
 1. Statistics: Statistics is one of the most important components of data science. Statistics is a way
to collect and analyze the numerical data in a large amount and finding meaningful insights from
it.
 2. Domain Expertise: In data science, domain expertise binds data science together. Domain
expertise means specialized knowledge or skills of a particular area. In data science, there are
various areas for which we need domain experts.
 3. Data engineering: Data engineering is a part of data science, which involves acquiring,
storing, retrieving, and transforming the data. Data engineering also includes metadata (data about
data) to the data.
 4. Visualization: Data visualization is meant by representing data in a visual context so that
people can easily understand the significance of data. Data visualization makes it easy to access
the huge amount of data in visuals.
 5. Advanced computing: Heavy lifting of data science is advanced computing. Advanced
computing involves designing, writing, debugging, and maintaining the source code of computer
programs.
THANK YOU