人工神经网络56 研究生现代控制工程教案 人工智能控制 教材课程.pptVIP

Artificial Neural Networks - I Delta Rule a.k.a. Least Mean Squares Widrow-Hoff iterative delta rule (1960) Gradient descent of the error surface Guaranteed to find minimum error configuration in single layer ANNs Stochastic approximation of desired behaviour l=learning coefficient wij=connection from neuron xj to yi x=(x1,x2,...,xn) ANN input y=(y1,y2,...,yn) ANN output d=(d1,d2,...,dn) desired output (x,d) training example e=ANN error w11 w12 w13 w14 y1 y2 y3 x1 x2 x3 x4 Unsupervised Learning ANN adapts weights to cluster input data Hebbian learning Connection stimulus-response strengthened (hebbian) Competitive learning algorithms Kohonen ART Input weights adjusted to resemble stimulus Hebbian Learning Hebb postulate (1948) Correlation-based learning Connections between concurrently firing neurons are strengthened Experimentally verified (1973) w12 w11 x1 x2 y1 l=learning coefficient wij=connection from neuron xj to yi General Formulation Hebb postulate Kohonen Grossberg (ART) Learning principle for artificial neural networks ENERGY MINIMIZATION We need an appropriate definition of energy for artificial neural networks, and having that we can use mathematical optimisation techniques to find how to change the weights of the synaptic connections between neurons. ENERGY = measure of task performance error Neural network mathematics Inputs Output Neural network mathematics Neural network: input / output transformation W is the matrix of all weight vectors. MLP neural networks MLP = multi-layer perceptron Perceptron: MLP neural network: x yout x yout RBF neural networks RBF = radial basis function Example: Gaussian RBF x yout Neural network tasks control classification prediction approximation These can be reformulated in general as FUNCTION APPROXIMATION tasks. Approximation: given a set of values of a function g(x) build a neural network that approximates the g(x) values for any input x. Neural network approximation Task specification: Data: set of val