Neural Nets

1
Neural Nets

• How the brain achieves intelligence
• 1011 1mhz cpus

2
Concerns

• Representation
• What is it
• What can it do
• Learnability
• How can it be trained
• Efficiency
• Of Learning
• Of Learned concept

3
(No Transcript)
4
Wekas Neural Net Output on Iris

• Node 0 lt-gt Iris-Setosa
• Threshold -3.50 Node 3 -1.00 Node 4
  9.07 Node 5 -4.10
• Node 1 lt-gt Iris-versicolor
• Threshold 1.06 Node 3 3.89 Node 4
  -9.76 Node 5 -8.59
• Node 2 lt-gt Iris-viginica
• Threshold -1.00 Node 3 -4.21 Node 4
  -3.62 Node 5 8.80
• Node 3 Threshold 3.38
• sepallength 0.90 sepalwidth 1.56
  petallength -5.0 petalwidth -4.91
• Node 4 Threshold -3.33
• sepallength -1.11 sepalwidth 3.12
  petallength -4.13 petalwidth -4.07
• Node 5 Threshold -7.49
• sepallength -1.21 sepalwidth -3.53
  petallength 8.40 petalwidth 9.46

5
Representation Feed-Forward Neural Net

• DAG of perceptrons
• Leaf nodes take inputs
• Outputs node yield decisions
• Architecture no one knows how to build them.
• Weights trained by hill-climbing slow and
  guarantee of only local optimum.

6
Representational Power

• Any boolean function can be represented in
  disjunctive or conjunctive normal form.
• Disjunctive or of anded features.
• Since perceptron can learn or and and,
  2-layer network can represent any boolean
  function.

7
Neural Nets Work

• Disease diagnosis 90 accurate on prostate
  cancer prediction
• Handwritten Character Recognition (5-layer net)
  99 accurate
• NetTalk 80 hidden units, 28 inputs. 78
  accuracy. Sounds like child learning to talk.

8
Summary

• Neural nets can do multiple classes and
  regression
• Training is slow
• Performance is fast and high quality
• No one knows how to create architecture
• Neural nets tend to be incomprehensible