Download to read offline
More Related Content
Similar to Finger Biometric - Neural Network.ppt
Finger Biometric - Neural Network.ppt
- 1. 1 Finger Biometric Finger Biometric --Neural networks
- 2. Neural networks • Neuralnetworks are made up of many artificial neurons. • Each input into the neuron has its own weight associated with it illustrated by the red circle. • A weight is simply a floating point number and it's these we adjust when we eventually come to train the network. 2
- 3. Neural networks • Aneuron can have any number of inputs from one to n, where n is the total number of inputs. • The inputs may be represented therefore as x1, x2, x3… xn. • And the corresponding weights for the inputs as w1, w2, w3… wn. • Output a = x1w1+x2w2+x3w3... +xnwn 3
- 4. How do weactually use an artificial neuron? • Feedforward network: The neurons in each layer feed their output forward to the next layer until we get the final output from the neural network. • There can be any number of hidden layers within a feedforward network. • The number of neurons can be completely arbitrary. 4
- 5. Neural Networks byan Example • let's design a neural network that will detect the number '4'. • Given a panel made up of a grid of lights which can be either on or off, we want our neural net to let us know whenever it thinks it sees the character '4'. • The panel is eight cells square and looks like this: • the neural net will have 64 inputs, each one representing a particular cell in the panel and a hidden layer consisting of a number of neurons (more on this later) all feeding their output into just one neuron in the output layer 5
- 6. Neural Networks byan Example • initialize the neural net with random weights • feed it a series of inputs which represent, in this example, the different panel configurations • For each configuration we check to see what its output is and adjust the weights accordingly so that whenever it sees something looking like a number 4 it outputs a 1 and for everything else it outputs a zero. • More: http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/rep ort.html 6
- 7.
- 8. We will introducethe MLP and the backpropagation algorithm which is used to train it MLP used to describe any general feedforward (no recurrent connections) network However, we will concentrate on nets with units arranged in layers x1 xn 8
- 9. Different books referto the above as either 4 layer (no. of layers of neurons) or 3 layer (no. of layers of adaptive weights). We will follow the latter convention 1st question: what do the extra layers gain you? Start with looking at what a single layer can’t do x1 xn 9
- 10. Perceptron Learning Theorem •Recap: A perceptron (threshold unit) can learn anything that it can represent (i.e. anything separable with a hyperplane) 10
- 11. The Exclusive ORproblem A Perceptron cannot represent Exclusive OR since it is not linearly separable. 11
- 12.
- 13. Minsky & Papert(1969) offered solution to XOR problem by combining perceptron unit responses using a second layer of Units. Piecewise linear classification using an MLP with threshold (perceptron) units 1 2 +1 +1 3 13
- 14.
- 15. Properties of architecture •No connections within a layer y f w x b i ij j i j m ( ) 1 Each unit is a perceptron 15
- 16. Properties of architecture •No connections within a layer • No direct connections between input and output layers • y f w x b i ij j i j m ( ) 1 Each unit is a perceptron 16
- 17. Properties of architecture •No connections within a layer • No direct connections between input and output layers • Fully connected between layers • y f w x b i ij j i j m ( ) 1 Each unit is a perceptron 17
- 18. Properties of architecture •No connections within a layer • No direct connections between input and output layers • Fully connected between layers • Often more than 3 layers • Number of output units need not equal number of input units • Number of hidden units per layer can be more or less than input or output units y f w x b i ij j i j m ( ) 1 Each unit is a perceptron Often include bias as an extra weight 18
- 19. What do eachof the layers do? 1st layer draws linear boundaries 2nd layer combines the boundaries 3rd layer can generate arbitrarily complex boundaries 19
- 20. Backward pass phase:computes ‘error signal’, propagates the error backwards through network starting at output units (where the error is the difference between actual and desired output values) Forward pass phase: computes ‘functional signal’, feed forward propagation of input pattern signals through network Backpropagation learning algorithm ‘BP’ Solution to credit assignment problem in MLP. Rumelhart, Hinton and Williams (1986) (though actually invented earlier in a PhD thesis relating to economics) BP has two phases: 20
- 21. Conceptually: Forward Activity- Backward Error 21
- 22. Forward Propagation ofActivity • Step 1: Initialise weights at random, choose a learning rate η • Until network is trained: • For each training example i.e. input pattern and target output(s): • Step 2: Do forward pass through net (with fixed weights) to produce output(s) – i.e., in Forward Direction, layer by layer: • Inputs applied • Multiplied by weights • Summed • ‘Squashed’ by sigmoid activation function • Output passed to each neuron in next layer – Repeat above until network output(s) produced 22
- 23. Step 3. Back-propagationof error • Compute error (delta or local gradient) for each output unit δ k • Layer-by-layer, compute error (delta or local gradient) for each hidden unit δ j by backpropagating errors (as shown previously) Step 4: Next, update all the weights Δwij By gradient descent, and go back to Step 2 The overall MLP learning algorithm, involving forward pass and backpropagation of error (until the network training completion), is known as the Generalised Delta Rule (GDR), or more commonly, the Back Propagation (BP) algorithm 23
- 24. ‘Back-prop’ algorithm summary (withMaths!) (Not Examinable) 24
- 25. ‘Back-prop’ algorithm summary (withNO Maths!) 25
- 26. MLP/BP: A workedexample 26
- 27. Worked example: ForwardPass 27
- 28. Worked example: ForwardPass 28
- 29. Worked example: BackwardPass 29
- 30. Worked example: UpdateWeights Using Generalized Delta Rule (BP) 30
- 31. Similarly for theall weights wij: 31
- 32. Verification that itworks 32
- 33. Training • This wasa single iteration of back-prop • Training requires many iterations with many training examples or epochs (one epoch is entire presentation of complete training set) • It can be slow ! • Note that computation in MLP is local (with respect to each neuron) • Parallel computation implementation is also possible 33
- 34. Training and testingdata • How many examples ? – The more the merrier ! • Disjoint training and testing data sets – learn from training data but evaluate performance (generalization ability) on unseen test data • Aim: minimize error on test data 34