ANN_B.TechPresentation of ANN basics.ppt
- 1. INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS (ANN) Sachin
- 2. The idea of ANNs..? 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
- 3. 3 Neural networks to the rescue… • Neural network: information processing paradigm inspired by biological nervous systems, such as our brain • Structure: large number of highly interconnected processing elements (neurons) working together • Like people, they learn from experience (by example)
- 4. 4 Definition of ANN “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”
- 5. Artificial Neurons ANN is an information processing system that has certain performance characteristics in common with biological nets. Several key features of the processing elements of ANN are suggested by the properties of biological neurons: 1. The processing element receives many signals. 2. Signals may be modified by a weight at the receiving synapse. 3. The processing element sums the weighted inputs. 4. Under appropriate circumstances (sufficient input), the neuron transmits a single output. 5. The output from a particular neuron may go to many other neurons.
- 6. 6 • From experience: examples / training data • Strength of connection between the neurons is stored as a weight- value for the specific connection. • Learning the solution to a problem = changing the connection weights A physical neuron An artificial neuron Artificial Neurons
- 7. Artificial Neurons ANNs have been developed as generalizations of mathematical models of neural biology, based on the assumptions that: 1. Information processing occurs at many simple elements called neurons. 2. Signals are passed between neurons over connection links. 3. Each connection link has an associated weight, which, in typical neural net, multiplies the signal transmitted. 4. Each neuron applies an activation function to its net input to determine its output signal.
- 8. 8 Four basic components of a human biological neuron The components of a basic artificial neuron Artificial Neuron
- 9. 9 Model Of A Neuron f() Y Wa Wb Wc Connection weights Summing function computation X1 X3 X2 Input units (dendrite) (synapse) (axon) (soma)
- 10. 10 • A neural net consists of a large number of simple processing elements called neurons, units, cells or nodes. • Each neuron is connected to other neurons by means of directed communication links, each with associated weight. • The weight represent information being used by the net to solve a problem.
- 11. 11 • Each neuron has an internal state, called its activation or activity level, which is a function of the inputs it has received. Typically, a neuron sends its activation as a signal to several other neurons. • A neuron can send only one signal at a time, although that signal is broadcast to several other neurons.
- 12. 12 • Neural networks are configured for a specific application, such as pattern recognition or data classification, through a learning process • In a biological system, learning involves adjustments to the synaptic connections between neurons same for artificial neural networks (ANNs)
- 13. 13 Characterization Characterization • Architecture – a pattern of connections between neurons • Single Layer Feedforward • Multilayer Feedforward • Recurrent • Strategy / Learning Algorithm – a method of determining the connection weights • Supervised • Unsupervised • Reinforcement • Activation Function – Function to compute output signal from input signal
- 14. 14 Single Layer Feedforward NN Single Layer Feedforward NN x2 w11 w12 x1 w21 w22 ym yn Input layer output layer Contoh: ADALINE, AM, Hopfield, LVQ, Perceptron, SOFM
- 15. 15 Multilayer Neural Network Multilayer Neural Network x2 V11 w12 x1 xm z1 V1n zn z2 Vmn Input layer Hidden layer Output layer y1 y2 Contoh: CCN, GRNN, MADALINE, MLFF with BP, Neocognitron, RBF, RCE w11 w12
- 16. 16 Recurrent NN Recurrent NN Input Contoh: ART, BAM, BSB, Boltzman Machine, Cauchy Machine, Hopfield, RNN Hidden nodes Outputs
- 17. 17 Strategy / Learning Algorithm Strategy / Learning Algorithm • Learning is performed by presenting pattern with target • During learning, produced output is compared with the desired output – The difference between both output is used to modify learning weights according to the learning algorithm • Recognizing hand-written digits, pattern recognition and etc. • Neural Network models: perceptron, feed-forward, radial basis function, support vector machine. Supervised Learning
- 18. 18 • Targets are not provided • Appropriate for clustering task – Find similar groups of documents in the web, content addressable memory, clustering. • Neural Network models: Kohonen, self organizing maps, Hopfield networks. Unsupervised Learning
- 19. 19 • Target is provided, but the desired output is absent. • The net is only provided with guidance to determine the produced output is correct or vise versa. • Weights are modified in the units that have errors Reinforcement Learning
- 20. Medical Applications Information Searching & retrieval Business & Management Education Chemistry ANN Applications
- 21. 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 Applications of ANNs
- 22. 22 NON-LINEARITY It can model non-linear systems INPUT-OUTPUT MAPPING It can derive a relationship between a set of input & output responses ADAPTIVITY The ability to learn allows the network to adapt to changes in the surrounding environment EVIDENTIAL RESPONSE It can provide a confidence level to a given solution Advantages Of NN
- 23. 23 CONTEXTUAL INFORMATION Knowledge is presented by the structure of the network. Every neuron in the network is potentially affected by the global activity of all other neurons in the network. Consequently, contextual information is dealt with naturally in the network. FAULT TOLERANCE Distributed nature of the NN gives it fault tolerant capabilities NEUROBIOLOGY ANALOGY Models the architecture of the brain Advantages Of NN
- 24. Thank You 24