Artificial Neural Networks : An Introduction

1. Artificial Neural Networks : An Introduction G.Anuradha

2. Learning Objectives • Reasons to study neural computation • Comparison between biological neuron and artificial neuron • Basic models of ANN • Different types of connections of NN, Learning and activation function • Basic fundamental neuron model-McCulloch-Pitts neuron and Hebb network

3. Reasons to study neural computation • To understand how brain actually works • Computer simulations are used for this purpose • To understand the style of parallel computation inspired by neurons and their adaptive connections • Different from sequential computation • To solve practical problems by using novel learning algorithms inspired by brain

4. Biological Neural Network

5. Neuron and a sample of pulse train

6. How does the brain work • Each neuron receives inputs from other neurons • Use spikes to communicate • The effect of each input line on the neuron is controlled by a synaptic weight • Positive or negative • Synaptic weight adapts so that the whole network learns to perform useful computations • Recognizing objects, understanding languages, making plans, controlling the body • There are 1011 neurons with 104 weights.

7. Modularity and brain • Different bits of the cortex do different things • Local damage to the brain has specific effects • Early brain damage makes function relocate • Cortex gives rapid parallel computation plus flexibility • Conventional computers requires very fast central processors for long sequential computations

8. Information flow in nervous system

9. ANN • ANN posess a large number of processing elements called nodes/neurons which operate in parallel. • Neurons are connected with others by connection link. • Each link is associated with weights which contain information about the input signal. • Each neuron has an internal state of its own which is a function of the inputs that neuron receives- Activation level

10. Comparison between brain verses computer

11. Artificial Neural Networks x1 X1 w1 y Y x2 w2 X2

12. McCulloch-Pitts Neuron Model

13. McCulloch Pits for And and or model

14. McCulloch Pitts for NOT Model

15. Advantages and Disadvantages of McCulloch Pitt model • Advantages • Simplistic • Substantial computing power • Disadvantages • Weights and thresholds are fixed • Not very flexible

16. Features of McCulloch-Pitts model • Allows binary 0,1 states only • Operates under a discrete-time assumption • Weights and the neurons’ thresholds are fixed in the model and no interaction among network neurons • Just a primitive model

17. General symbol of neuron consisting of processing node and synaptic connections

18. Neuron Modeling for ANN Is referred to activation function. Domain is set of activation values net. Scalar product of weight and input vector Neuron as a processing node performs the operation of summation of its weighted input.

19. Binary threshold neurons • There are two equivalent ways to write the equations for a binary threshold neuron: 1 if 1 if 0 otherwise 0 otherwise

20. Sigmoid neurons • These give a real-valued output that is a smooth and bounded function of their total input. • Typically they use the logistic function • They have nice derivatives which make learning easy 1 0.5 0 0

21. Activation function • Bipolar binary and unipolar binary are called as hard limiting activation functions used in discrete neuron model • Unipolar continuous and bipolar continuous are called soft limiting activation functions are called sigmoidal characteristics.

22. Activation functions Bipolar continuous Bipolar binary functions

23. Activation functions Unipolar continuous Unipolar Binary

24. Common models of neurons Binary perceptrons Continuous perceptrons

25. Quiz • Which of the following tasks are neural networks good at? • Recognizing fragments of words in a pre-processed sound wave. • Recognizing badly written characters. • Storing lists of names and birth dates. • logical reasoning Neural networks are good at finding statistical regularities that allow them to recognize patterns. They are not good at flawlessly applying symbolic rules or storing exact numbers.

26. Basic models of ANN

27. Classification based on interconnections

28. These are the commonest type of neural network in practical applications. The first layer is the input and the last layer is the output. If there is more than one hidden layer, we call them “deep” neural networks. They compute a series of transformations that change the similarities between cases. The activities of the neurons in each layer are a non-linear function of the activities in the layer below. Feed-forward neural networks output units hidden units input units

29. Feedforward Network • Its output and input vectors are respectively • Weight wij connects the i’th neuron with j’th input. Activation rule of ith neuron is where EXAMPLE

30. Multilayer feed forward network Can be used to solve complicated problems

31. Feedback network When outputs are directed back as inputs to same or preceding layer nodes it results in the formation of feedback networks

32. Lateral feedback If the feedback of the output of the processing elements is directed back as input to the processing elements in the same layer then it is called lateral feedback

33. These have directed cycles in their connection graph. That means you can sometimes get back to where you started by following the arrows. They can have complicated dynamics and this can make them very difficult to train. There is a lot of interest at present in finding efficient ways of training recurrent nets. They are more biologically realistic. Recurrent networks Recurrent nets with multiple hidden layers are just a special case that has some of the hiddenhidden connections missing.

34. Recurrent neural networks for modeling sequences time  • Recurrent neural networks are a very natural way to model sequential data: • They are equivalent to very deep nets with one hidden layer per time slice. • Except that they use the same weights at every time slice and they get input at every time slice. • They have the ability to remember information in their hidden state for a long time. • But its very hard to train them to use this potential. output output output hidden hidden hidden input input input

35. An example of what recurrent neural nets can now do (to whet your interest!) • Ilya Sutskever (2011) trained a special type of recurrent neural net to predict the next character in a sequence. • After training for a long time on a string of half a billion characters from English Wikipedia, he got it to generate new text. • It generates by predicting the probability distribution for the next character and then sampling a character from this distribution.

36. Symmetrically connected networks • These are like recurrent networks, but the connections between units are symmetrical (they have the same weight in both directions). • John Hopfield (and others) realized that symmetric networks are much easier to analyze than recurrent networks. • They are also more restricted in what they can do. because they obey an energy function. • For example, they cannot model cycles. • Symmetrically connected nets without hidden units are called “Hopfield nets”.

37. Symmetrically connected networks with hidden units • These are called “Boltzmann machines”. • They are much more powerful models than Hopfield nets. • They are less powerful than recurrent neural networks. • They have a beautifully simple learning algorithm.

38. Basic models of ANN

39. Learning • It’s a process by which a NN adapts itself to a stimulus by making proper parameter adjustments, resulting in the production of desired response • Two kinds of learning • Parameter learning:- connection weights are updated • Structure Learning:- change in network structure

40. Training • The process of modifying the weights in the connections between network layers with the objective of achieving the expected output is called training a network. • This is achieved through • Supervised learning • Unsupervised learning • Reinforcement learning

41. Classification of learning • Supervised learning:- • Learn to predict an output when given an input vector. • Unsupervised learning • Discover a good internal representation of the input. • Reinforcement learning • Learn to select an action to maximize payoff.

42. Supervised Learning • Child learns from a teacher • Each input vector requires a corresponding target vector. • Training pair=[input vector, target vector] Neural Network W X Y (Actual output) (Input) Error (D-Y) signals Error Signal Generator (Desired Output)

43. Two types of supervised learning • Each training case consists of an input vector x and a target output t. • Regression: The target output is a real number or a whole vector of real numbers. • The price of a stock in 6 months time. • The temperature at noon tomorrow. • Classification: The target output is a class label. • The simplest case is a choice between 1 and 0. • We can also have multiple alternative labels.

44. Unsupervised Learning • How a fish or tadpole learns • All similar input patterns are grouped together as clusters. • If a matching input pattern is not found a new cluster is formed • One major aim is to create an internal representation of the input that is useful for subsequent supervised or reinforcement learning. • It provides a compact, low-dimensional representation of the input.

45. Self-organizing • In unsupervised learning there is no feedback • Network must discover patterns, regularities, features for the input data over the output • While doing so the network might change in parameters • This process is called self-organizing

46. Reinforcement Learning X NN W Y (Input) (Actual output) Error signals Error Signal Generator R Reinforcement signal

47. When Reinforcement learning is used? • If less information is available about the target output values (critic information) • Learning based on this critic information is called reinforcement learning and the feedback sent is called reinforcement signal • Feedback in this case is only evaluative and not instructive

48. Basic models of ANN

49. Activation Function • Identity Function • f(x)=x for all x • Binary Step function • Bipolar Step function • Sigmoidal Functions:- Continuous functions • Ramp functions:-

50. Some learning algorithms we will learn are • Supervised: • Adaline, Madaline • Perceptron • Back Propagation • multilayer perceptrons • Radial Basis Function Networks • Unsupervised • Competitive Learning • Kohenen self organizing map • Learning vector quantization • Hebbian learning