Introduction to neural network (Module 1).pptx
•
0 likes•148 views
useful to understand the basics of neural network
Report
Share
More Related Content
Similar to Introduction to neural network (Module 1).pptx
Similar to Introduction to neural network (Module 1).pptx (20)
Recently uploaded
Recently uploaded (20)
Introduction to neural network (Module 1).pptx
- 1. Introduction to Neural Networks (Module 1) Archana Chaudhari, DJSCE
- 2. DEFINITION OF NEURAL NETWORKS • According to the DARPA Neural Network Study (1988, AFCEA International Press, p. 60): • • ... a neural network is a system composed of many simple processing elements operating in parallel whose function is determined by network structure, connection strengths, and the processing performed at computing elements or nodes. • According to Haykin (1994), p. 2: • A neural network is a massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects: • Knowledge is acquired by the network through a learning process. • Interneuron connection strengths known as synaptic weights are used to store the knowledge. 7/1/2024 Introduction to Neural Networks 2
- 3. What is Artificial Intelligence • How google translates entire webpage in a matter of seconds • Phone gallery groups images based on the location • Identify faces of young, middle aged and old persons 7/1/2024 Introduction to Neural Networks 3
- 4. • Deep learning is a subset of Machine Learning • Machine learning is subset of Artificial Intelligence • AI is a technique which is able to mimic human behaivour 7/1/2024 Introduction to Neural Networks 4
- 5. • Artificial Neural network is a type machine learning inspired by the structure of the human brain. • Deep learning is advanced form of Artificial Neural Network. 7/1/2024 Introduction to Neural Networks 5
- 6. ANN • Artificial Neural Networks (ANN) • Information processing paradigm inspired by biological nervous systems • ANN is composed of a system of neurons connected by synapses • ANN learn by example • Adjust synaptic connections between neurons 7/1/2024 Introduction to Neural Networks 6
- 7. Organization of brain • The human brain contains about 10 billion nerve cells, or neurons. • On average, each neuron is connected to other neurons through approximately 10,000 synapses. 7/1/2024 Introduction to Neural Networks 7
- 8. 7/1/2024 Introduction to Neural Networks 8
- 9. BIOLOGICAL (MOTOR) NEURON Dendrite: Receives signals from other neurons Soma: Processes the information Axon: Transmits the output of this neuron Synapse: Point of connection to other neurons 7/1/2024 Introduction to Neural Networks 9
- 10. ARTIFICIAL NEURAL NET • Information-processing system. • Neurons process the information. • The signals are transmitted by means of connection links. • The links possess an associated weight. • The output signal is obtained by applying activations to the net input. 7/1/2024 Introduction to Neural Networks 10
- 11. MOTIVATION FOR NEURAL NET • Scientists are challenged to use machines more effectively for tasks currently solved by humans. • Symbolic rules don't reflect processes actually used by humans. • Traditional computing excels in many areas, but not in others. 7/1/2024 Introduction to Neural Networks 11
- 12. Biological and Artificial Neuron Models 7/1/2024 Introduction to Neural Networks 12
- 13. Neuron Model 7/1/2024 Introduction to Neural Networks 13
- 14. Neuron Model • Neuron collects signals from dendrites • Sends out spikes of electrical activity through an axon, which splits into thousands of branches. • At end of each branch, a synapses converts activity into either exciting or inhibiting activity of a dendrite at another neuron. • Neuron fires when exciting activity surpasses inhibitory activity • Learning changes the effectiveness of the synapses 7/1/2024 Introduction to Neural Networks 14
- 15. Characteristics of ANN • It contains huge number of interconnected processing elements called neurons to do all operations • Information stored in the neurons are basically the weighted linkage of neurons • The input signals arrive at the processing elements through connections and connecting weights. • It has the ability to learn , recall and generalize from the given data by suitable assignment and adjustment of weights. • The collective behavior of the neurons describes its computational power, and no single neuron carries specific information . 7/1/2024 Introduction to Neural Networks 15
- 16. ARTIFICIAL NEURAL NET • The figure shows a simple artificial neural net with two input neurons (X1, X2) and one output neuron (Y). • The inter connected weights are given by W1 and W2. X2 X1 W2 W1 Y 7/1/2024 Introduction to Neural Networks 16
- 17. McCULLOCH–PITTS NEURON • The earliest ANN model • Inputs could be either 0 or 1 • threshold function as an activation function • the output signal yout is 1 if the input ysum is greater than or equal to a given threshold value, else 0. • can be used to design logical operations 7/1/2024 Introduction to Neural Networks 17
- 18. Example • John carries an umbrella if it is sunny or if it is raining. There are four given situations. I need to decide when John will carry the umbrella. The situations are as follows: • First scenario: It is not raining, nor it is sunny • Second scenario: It is not raining, but it is sunny • Third scenario: It is raining, and it is not sunny • Fourth scenario: It is raining as well as it is sunny • To analyse the situations using the McCulloch-Pitts neural model, I can consider the input signals as follows: • X1: Is it raining? • X2 : Is it sunny? • So, the value of both scenarios can be either 0 or 1. We can use the value of both weights X1 and X2 as 1 and a threshold function as 1. So, the neural network model will look like: 7/1/2024 Introduction to Neural Networks 18
- 19. Situati on x1 x2 ysum yout 1 0 0 0 0 2 0 1 1 1 3 1 0 1 1 4 1 1 2 1 I can conclude that in the situations where the value of yout is 1, John needs to carry an umbrella 7/1/2024 Introduction to Neural Networks 19
- 20. Historical Developments • 1943: McCulloch and Pitts model neural networks based on their understanding of neurology. – Neurons embed simple logic functions: • a or b • a and b • 1950s: – Farley and Clark • IBM group that tries to model biological behavior • Consult neuro-scientists at McGill, whenever stuck – Rochester, Holland, Haibit and Duda 7/1/2024 Introduction to Neural Networks 20
- 21. Historical Developments • Perceptron (Rosenblatt 1958) – Three layer system: • Input nodes • Output node • Association layer – Can learn to connect or associate a given input to a random output unit • Minsky and Papert – Showed that a single layer perceptron cannot learn the XOR of two binary inputs – Lead to loss of interest (and funding) in the field 7/1/2024 Introduction to Neural Networks 21
- 22. Historical Developments • Perceptron (Rosenblatt 1958) – Association units A1, A2, … extract features from user input – Output is weighted and associated – Function fires if weighted sum of input exceeds a threshold. 7/1/2024 Introduction to Neural Networks 22
- 23. Historical Developments • Back-propagation learning method (Werbos 1974) – Three layers of neurons • Input, Output, Hidden – Better learning rule for generic three layer networks – Regenerates interest in the 1980s • Successful applications in medicine, marketing, risk management, … (1990) 7/1/2024 Introduction to Neural Networks 23
- 24. Potential Applications of ANN • Massive parallelism • Distributed representation and computation • Learning ability • Generalization ability • Adaptivity • Inherent contextual information processing • Fault tolerance • Low energy consumption. 7/1/2024 Introduction to Neural Networks 24