NeuralNetwork(神经网络自学的英文材料).pptVIP

Hamming Operation Second Layer Hopfield Network Apple/Banana Problem Test: “Rough” Banana (Banana) Summary Perceptron Feedforward Network Linear Decision Boundary One Neuron for Each Decision Hamming Network Competitive Network First Layer – Pattern Matching (Inner Product) Second Layer – Competition (Winner-Take-All) # Neurons = # Prototype Patterns Hopfield Network Dynamic Associative Memory Network Network Output Converges to a Prototype Pattern # Neurons = # Elements in each Prototype Pattern Perceptron Learning Rule Learning Rules ? Supervised Learning Network is provided with a set of examples of proper network behavior (inputs/targets) ? Reinforcement Learning Network is only provided with a grade, or score, which indicates network performance ? Unsupervised Learning Only network inputs are available to the learning algorithm. Network learns to categorize (cluster) the inputs. Perceptron Architecture W w 1 1 , w 1 2 , ? w 1 R , w 2 1 , w 2 2 , ? w 2 R , w S 1 , w S 2 , ? w S R , = w i w i 1 , w i 2 , w i R , = W w T 1 w T 2 w T S = Single-Neuron Perceptron Decision Boundary ? All points on the decision boundary have the same inner product with the weight vector. ? Therefore they have the same projection onto the weight vector, and they must lie on a line orthogonal to the weight vector Example - OR OR Solution Weight vector should be orthogonal to the decision boundary. Pick a point on the decision boundary to find the bias. Multiple-Neuron Perceptron Each neuron will have its own decision boundary. A single neuron can classify input vectors into two categories. A multi-neuron perceptron can classify input vectors into 2S categories. Learning Rule Test Problem Starting Point Present p1 to the network: Random initial weight: Incorrect Classification. Tentative Learning Rule ? Set 1w to p1 – Not stable ? Add p1 to 1w Tentative Rule: Second Input Vector (Incorrect Classification) Modification to Rule: Third Input Vector Patterns are now correctly cl