lecture3

# lecture3 - Articial Intelligence (Articial) Neural Networks...

This preview shows pages 1–6. Sign up to view the full content.

Neural Networks; page 1 of 19 Artiﬁcial Intelligence (Artiﬁcial) Neural Networks pronunciation (cat vs. cent) handwritten character recognition face detection driving “neural networks are the second best way of doing just about anything” Russell and Norvig - Chapter 20 Nilsson - Chapter 3

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Neural Networks; page 2 of 19 F1 t t f f F2 t f t f F3 f f f t F4 t f t f ... ... ... ... ... t t f t fttt. . . ??? features class training examples abcd f(a,b,c,d) bias here: “smooth interpolation between data points” inductive learning problem ﬁnd a function that is consistent with all training examples and that we believe will make the fewest mistakes on the examples with unknown classes
Neural Networks; page 3 of 19 perceptron 0..1 0..1 0..1 g(w 1 x 1 + w 2 x 2 + . ..) x1 x2 w1 w2 output 0 1 threshold x g(x) our ultimate task: learn the weights and thresholds in a network of perceptrons learning takes time, classiﬁcation is fast Axon Cell body or Soma Nucleus Dendrite Synapses Axonal arborization Axon from another cell Synapse inputs weights

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Neural Networks; page 4 of 19 examples of perceptrons (1) -1.0 0 = false 1 = true NOT 1.0 1.0 OR 1.0 1.0 AND threshold 1.5 threshold 0.5 threshold -0.5 we can represent every propositional sentence using a network of perceptrons the value of the threshold makes a difference
Neural Networks; page 5 of 19 linear separability w 1 x 1 + w 2 x 2 = threshold w 1 x 1 = threshold - w 2 x 2 x 1 = (threshold / w 1 ) - (w 2 / w 1 ) x 2 x 2 x 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## lecture3 - Articial Intelligence (Articial) Neural Networks...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online