Downloaded 23 times
More Related Content
Neural network
- 1. Neural Network SUBMITTED TO:NADIRA ANJUM
- 2. Team MembersFairin Rahman172-15-915 Tanjila Jahan Any 172-15-905 Mst. Umme Faria Tamanna 172-15-909 Arfana Chamok 172-15-911
- 3. Neural networks area series of algorithms that mimic the operations of a human brain to recognize relationships between vast amounts of data. Neural networks can adapt to changing input; so the network generates the best possible result without needing to redesign the output criteria It is either a biological neural network, made up of real biological neurons, or an artificial neural network, for solving artificial intelligence (AI) problems. What is neural network?
- 4. Biological Neuron Network Composedof a groups of chemically connected or functionally associated neurons. A single neuron may be connected to many other neurons. Connections, called synapses, are usually formed from axons to dendrites, though dendrodendritic synapse and other connections are possible Apart from the electrical signaling, there are other forms of signaling that arise from neurotransmitter diffusion.
- 6. Neural Signal Processing Signalsfrom connected neurons are collected by the dendrites. The cells body (soma) sums the incoming signals (spatially and temporally) When sufficient input is received (i.e., a threshold is exceeded), the neuron generates an action potential or ‘spike’ (i.e., it ‘fires’). That action potential is transmitted along the axon to other neurons, or to structures outside the nervous systems (e.g., muscles). If sufficient input is not received (i.e. the threshold is notexceeded), the inputs quickly decay and no action potential is generated. Timing is clearly important – input signals must arrive together, strong inputs will generate more action potentials per unit time.
- 7. Artificial Neural Network Anartificial neural network (ANN) is the component of artificial intelligence that is meant to simulate the functioning of a human brain. Processing units make up ANNs, which in turn consist of inputs and outputs. The inputs are what the ANN learns from to produce the desired output. Backpropagation is the set of learning rules used to guide artificial neural networks. The practical applications for ANNs are far and wide, encompassing finance, personal communication, industry, education, and so on.
- 8. The ANN Application Classification,the aim is to predict the class of an input vector Pattern matching, the aim is to produce a pattern best associated with a given input vector. Pattern completion, the aim is to complete the missing parts of a given input vector. Optimization, the aim is to find the optimal values of parameters in an optimization problem Control, an appropriate action is suggested based on given an input vectors. Function approximation/times series modeling, the aim is to learn the functional relationships between input and desired output vectors Data mining, with the aim of discovering hidden patterns from data (knowledge discovery)
- 9. How does ANNwork? Artificial Neural Networks can be best viewed as weighted directed graphs, where the nodes are formed by the artificial neurons and the connection between the neuron outputs and neuron inputs can be represented by the directed edges with weights. The Artificial Neural Network receives the input signal from the external world in the form of a pattern and image in the form of a vector. These inputs are then mathematically designated by the notations x(n) for every n number of inputs. These weights typically represent the strength of the interconnection amongst neurons inside the artificial neural network All the weighted inputs are summed up inside the computing unit
- 10. Continued.... If the weightedsum equates to zero, a bias is added to make the output non-zero or else to scale up to the system’s response Bias has the weight and the input to it is always equal to 1. The sum of weighted inputs can be in the range of 0 to positive infinity. To keep the response in the limits of the desired value, a certain threshold value is benchmarked The sum of weighted inputs is passed through theactivation function.
- 11. Difference between ANNand BNN Artificial Neural Network Biological Neural NetworkCharacteristics Speed Faster in processing information. Response time is in nanoseconds Slower in processing information. The response time is in milliseconds. Processing Serial processing. Massively parallel processing. Size & Complexity Less size & complexity. It does not perform complex pattern recognition tasks. More size & complexity
- 12. Continued. . .. Artificial Neural Network Biological Neural NetworkCharacteristics Storage Highly complex and dense network of interconnected neurons Fault tolerance Information storage is replaceable means new data can be added by deleting an old one. Fault intolerant. Information once corrupted cannot be retrieved in case of failure of the system. Control Mechanism There is a control unit for controlling computing activities Information storage is adaptable means new information is added by adjusting the interconnection strengths without destroying old information No specific control mechanism external to the computing task.
- 13. Similarities between ANNAnd BNN There is few similarities between ANN and BNN too.Neural Networks resemble the human brain in the following two ways – A neural network acquires knowledge through learning. A neural network’s knowledge is stored within inter- neuron connection strengths known as synaptic weights.
- 14. Types of NeuralNetworks in Artificial Intelligence Types DescriptionParameter Based on the connection pattern FeedForward, Recurrent Feedforward – In which graphs have no loops. Recurrent – Loopsoccur because of feedback. Based on the number of hidden layers Single-layer, Multi-Layer Single Layer – Havingone hidden layer. E.g. , Single Perceptron Multilayer – Having multiple hidden layers. Multilayer Perceptron
- 15. Continued. . .. Types DescriptionParameter Based on the nature of weights Fixed, Adaptive Fixed – Weights are fixeda priori and not changed at all. Adaptive – Weights are updated and changed during training. Based on Memory unit Static, Dynamic Static – Memorylessunit. The current output depends on the current input. E.g. , Feedforward network Dynamic – Memory unit – The output depends upon the current input as well as the current output. E.g. , Recurrent Neural Network
- 16. CommonArchitectures of Neural Network Perceptron BoltzmannMachine Deep Belief Networks Convolutional Neural Network Autoencoders Recurrent Neural Networks Long/Short Term Memory Gated Recurrent Unit Hopefield Network Generative Adversarial Network
- 17. Application of NeuralNetwork The Artificial Neural Network has been in existence from 1943, when it was initially designed, but has only recently come into light under Artificial Intelligence due to the applications that make it more preferable. These include: Image processing Language processing and translation Route detection Speech recognition Forecasting
- 18. Advantages of NeuralNetwork NeuralNetworks have the ability to learn by themselves and produce the output that is not limited to the input provided to them. The input is stored in its own networks instead of a database, hence the loss of data does not affect its working. These networks can learn from examples and apply them when a similar event arises, making them able to work through real-time events. Even if a neuron is not responding or a piece of information is missing,the network can detect the fault and still produce the output. They can perform multiple tasks in parallel without affecting the system performance.
- 19. Limitations of NeuralNetwork The neural network needs the training to operate. The architecture of a neural network is different from the architecture of microprocessors, therefore, needs to be emulated. Requires high processing time for large neural networks.