CSE P573 Applications of Artificial Intelligence Neural Networks

1
CSE P573Applications of Artificial
IntelligenceNeural Networks

• Henry Kautz
• Autumn 2004

2
(No Transcript)
3
(No Transcript)
4
Perceptron (sigmoid unit)
weighted sum of inputs
constant term
soft threshold
5
(No Transcript)
6
Training a Neuron

• Idea adjust weights to reduce sum of squared
  errors over training set
• Error difference between actual and intended
  output
• Algorithm gradient descent
• Calculate derivative (slope) of error function
• Take a small step in the downward direction
• Step size is the training rate

7
Gradient of the Error Function
8
Gradient of the Error Function
9
Single Unit Training Rule

• In short adjust weights on inputs that were on
  in proportion to the error and the size of the
  output

10
Beyond Perceptrons

• Single units can learn any linear function
• Single layer of units can learn any set of linear
  inequalities
• Adding additional layers of hidden units
  between input and output allows any function to
  be learned!
• Hidden units trained by propagating errors back
  through the network

11
(No Transcript)
12
(No Transcript)
13
(No Transcript)
14
Character Recognition Demo
15
Beyond Backprop

• Backpropagation is the most common algorithm for
  supervised learning with feed-forward neural
  networks
• Many other learning rules for these and other
  cases have been studied

16
Hebbian Learning

• Alternative to backprop for unsupervised learning
• Increase weights on connected neurons whenever
  both fire simultaneously
• Neurologically plausible (Hebbs 1949)

17
Self-organizing maps (SOMs)

• Unsupervised learning for clustering inputs
• Winner take all network
• one cell per cluster
• Learning rule update weights near winning
  neuron to make it closer to the input

18
Recurrent Neural Networks

• Include time-delay feedback loops
• Can handle temporal data tasks, such as sequence
  prediction