Download presentation

1
**RBF Neural Networks x2 - + - 1 - + 2 - - - - x1**

Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does the job of separating the two classes? NN 3

2
Example 1 Let t1,t2 and r1, r2 be the center and radius of circles 1 and 2, respectively, x = (x1,x2) example _t1 x1 1 y x2 _t2 1 _t1(x) = 1 if distance of x from t1 less than r1 and 0 otherwise _t2(x) = 1 if distance of x from t2 less than r2 and 0 otherwise Hyperspheric radial basis function NN 3

3
**Example 1 _t2 - + - 2 - (0,1) + 1 - - - - _t1 (0,0) (1,0)**

Geometrically: examples are mapped to the feature space (_t1, _t2): examples in circle 2 are mapped to (0,1), examples in circle 1 are mapped to (1,0), and examples outside both circles are mapped to (0,0). The two classes become linearly separable in the (_t1, _t2) feature space! NN 3

4
**RBF ARCHITECTURE One hidden layer with RBF activation functions**

x2 xm x1 y wm1 w1 One hidden layer with RBF activation functions Output layer with linear activation function. NN 3

5
**Other Types of φ Inverse multiquadrics Gaussian functions (most used)**

NN 3

6
**Gaussian RBF φ φ : is a measure of how spread the curve is: center**

Large Small NN 3

7
**HIDDEN NEURON MODEL Hidden units: use radial basis functions**

φ( || x - t||) the output depends on the distance of the input x from the center t x1 φ( || x - t||) t is called center is called spread center and spread are parameters x2 xm NN 3

8
Hidden Neurons A hidden neuron is more sensitive to data points near its center. For Gaussian RBF this sensitivity may be tuned by adjusting the spread , where a larger spread implies less sensitivity. NN 3

9
**Example: the XOR problem**

(1,1) (0,1) (0,0) (1,0) x1 x2 Input space: Output space: Construct an RBF pattern classifier such that: (0,0) and (1,1) are mapped to 0, class C1 (1,0) and (0,1) are mapped to 1, class C2 y 1 NN 3

10
**Example: the XOR problem**

In the feature (hidden layer) space: When mapped into the feature space < 1 , 2 > (hidden layer), C1 and C2 become linearly separable. So a linear classifier with 1(x) and 2(x) as inputs can be used to solve the XOR problem. φ1 φ2 1.0 (0,0) 0.5 (1,1) Decision boundary (0,1) and (1,0) NN 3

11
**RBF NN for the XOR problem**

+1 -1 t2 y NN 3

12
**Application: FACE RECOGNITION**

The problem: Face recognition of persons of a known group in an indoor environment. The approach: Learn face classes over a wide range of poses using an RBF network. See the PhD thesis by Jonathan Howell NN 3

13
**Dataset Sussex database (university of Sussex)**

100 images of 10 people (8-bit grayscale, resolution 384 x 287) for each individual, 10 images of head in different pose from face-on to profile Designed to good performance of face recognition techniques when pose variations occur NN 3

14
Datasets (Sussex) All ten images for classes 0-3 from the Sussex database, nose-centred and subsampled to 25x25 before preprocessing NN 3

15
**RBF: parameters to learn**

What do we have to learn for a RBF NN with a given architecture? The centers of the RBF activation functions the spreads of the Gaussian RBF activation functions the weights from the hidden to the output layer Different learning algorithms may be used for learning the RBF network parameters. We describe three possible methods for learning centers, spreads and weights. NN 3

16
**Learning Algorithm 1 Centers: are selected at random**

centers are chosen randomly from the training set Spreads: are chosen by normalization: Then the activation function of hidden neuron becomes: NN 3

17
Learning Algorithm 1 Weights: are computed by means of the pseudo-inverse method. For an example consider the output of the network We would like for each example, that is NN 3

18
**Learning Algorithm 1 and for all the examples at the same time**

This can be re-written in matrix form for one example and for all the examples at the same time NN 3

19
**Learning Algorithm 1 let then we can write**

If is the pseudo-inverse of the matrix we obtain the weights using the following formula NN 3

20
**Learning Algorithm 1: summary**

NN 3

21
**Learning Algorithm 2: Centers**

clustering algorithm for finding the centers Initialization: tk(0) random k = 1, …, m1 Sampling: draw x from input space Similarity matching: find index of center closer to x Updating: adjust centers Continuation: increment n by 1, goto 2 and continue until no noticeable changes of centers occur NN 3

22
**Learning Algorithm 2: summary**

Hybrid Learning Process: Clustering for finding the centers. Spreads chosen by normalization. LMS algorithm for finding the weights. NN 3

23
Learning Algorithm 3 Apply the gradient descent method for finding centers, spread and weights, by minimizing the (instantaneous) squared error Update for: centers spread weights NN 3

24
Comparison with FF NN RBF-Networks are used for regression and for performing complex (non-linear) pattern classification tasks. Comparison between RBF networks and FFNN: Both are examples of non-linear layered feed-forward networks. Both are universal approximators. NN 3

25
**Comparison with multilayer NN**

Architecture: RBF networks have one single hidden layer. FFNN networks may have more hidden layers. Neuron Model: In RBF the neuron model of the hidden neurons is different from the one of the output nodes. Typically in FFNN hidden and output neurons share a common neuron model. The hidden layer of RBF is non-linear, the output layer of RBF is linear. Hidden and output layers of FFNN are usually non-linear. NN 3

26
**Comparison with multilayer NN**

Activation functions: The argument of activation function of each hidden neuron in a RBF NN computes the Euclidean distance between input vector and the center of that unit. The argument of the activation function of each hidden neuron in a FFNN computes the inner product of input vector and the synaptic weight vector of that neuron. Approximation: RBF NN using Gaussian functions construct local approximations to non-linear I/O mapping. FF NN construct global approximations to non-linear I/O mapping. NN 3

Similar presentations

© 2020 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google