Artificial neural network
- 2. Definition Human biological neuron Artificial Neuron Outline Applications of ANN 1 Advantages of ANN Disadvantages of ANN
- 3. TheideaofANNs? NNs learn relationship between cause and effect or organize large volumes of data into orderly and informative patterns. frog lion bird What is that? It’s a frog 2
- 5. Biological Neural Networks A Biological neuron has three components : AXON SOMA(CELL BODY) DENDRITES T 4
- 6. 6 AXON: It is the receiver SOMA: Connector to dendrites DENDRITES: IT takes input from other cells. WHATAMI MADEOF?
- 7. FunctionOf Neuron Neurons are the building blocks of the nervous system. They receive and transmit signals to different parts of the body. This is carried out in both physical and electrical forms. There are several different types of neurons that facilitate the transmission of information. 6
- 8. WHATIS ANN? It is a data processing system consisting of a large number of simple, highly interconnected processing elements (artificial neurons) in an architecture inspired by the structure of the cerebral cortex of the brain. 7
- 9. Arewe thesame? ANN Biological Neuron INPUT DENDRITES NODE SOMA OUTPUT AXON INTERCONNECTION SYNAPSE 8
- 10. 9 A physical neuron An artificial neuron A Graphical Analogy
- 11. Perceptrons 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. 10
- 12. Model Of A perceptron 11 f() Y Wa Wb Wc Connection weights Summing function computation X1 X3 X2 Input units (dendrite) (synapse) (axon) (soma)
- 13. Perceptron has following components : INPUT VALUES >>We pass input values to a neuron using this layer. It might be something as simple as a collection of array values. It is similar to a dendrite in biological neurons . 12
- 14. WEIGHT AND BIAS >> Weights are a collection of array values which are multiplied to the respective input values. We then take a sum of all these multiplied values which is called a weighted sum. Next, we add a bias value to the weighted sum to get final value for prediction by our neuron. 13
- 15. ACTIVATION FUNCTION >> Activation Function decides whether or not a neuron is fired. It decides which of the two output values should be generated by the neuron. 14
- 16. OUTPUT LAYER >> Output layer gives the final output of a neuron which can then be passed to other neurons in the network or taken as the final output value. 15
- 17. HOWDOESANNWORKS Artificial neural networks (ANNs) are comprised of a node layers, containing an input layer, one or more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and has an associated weight and threshold. Once an input layer is determined, weights are assigned. These help determine the importance of any given variable, with larger contributing more significantly to the output compared to other Their respective weights and then summed. Afterward, the output passed through an activation function, which determines the If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. 16
- 18. HowDoes ANNLearns? Typically, an ANN is initially trained or fed large amounts of data. Training consists of providing input and telling the network what the output should be. For example, to build a network that identifies the faces of actors, the initial training might be a series of pictures, including actors, non-actors, masks, statuary and animal faces. Each input is accompanied by the matching identification, such as actors' names or "not actor" or "not human" information. Providing the answers allows the model to adjust its internal weightings to learn how to do its job better. 17
- 19. Advantages Of ANN Parallel processing abilities mean the network can perform more than one job at a time. Information is stored on an entire network, not just a database. Fault tolerance means the corruption of one or more cells of the ANN will not stop the generation of output. Gradual corruption means the network will slowly degrade over time, instead of a problem destroying the network instantly. ANN can learn from events and make decisions based on the observations. 18
- 20. Who is interested?... Electrical Engineers – signal processing, control theory Computer Engineers – robotics Computer Scientists – artificial intelligence, pattern recognition Mathematicians – modelling tool when explicit relationships are unknown 19
- 21. Signal processing Pattern recognition, e.g. handwritten characters or face identification. Diagnosis or mapping symptoms to a medical case. Speech recognition Human Emotion Detection Educational Loan Forecasting 20 ApplicationsofANN
- 22. Disadvantages Of ANN Artificial Neural Networks require processors with parallel processing power, by their structure. When ANN gives a probing solution, it does not give a clue as to why and how ? There is no specific rule for determining the structure of artificial neural networks. The appropriate network structure is achieved through experience and trial and error. The display mechanism to be determined will directly influence the performance of the network. This is dependent on the user's ability 21
- 23. FUTUREOF ANN Self Driving Cars More Advanced Digital ASSISTANTS Object Detection Powerful CPU’s Fake content detector in social media sites 22
- 24. Refrence https://www.geeksforgeeks.org/difference-between- ann-and-bnn/ https://viso.ai/deep-learning/artificial-neural-network/ https://towardsdatascience.com/whats-the-role-of- weights-and-bias-in-a-neural-network-4cf7e9888a0f https://dzone.com/articles/designing-a-neural- network-in-java-activation-func https://searchenterpriseai.techtarget.com/definition/ne ural-network 23
- 25. THANK YOU