Professional Documents
Culture Documents
L17 My Neural NW
L17 My Neural NW
January 2011
Noise Reduction
Recognize patterns in the inputs and produce noiseless outputs
Prediction
Extrapolation based on historical data
Very useful in Data Mining imitate a humans ability to learn from experience better results are the hope
(Adequately designed and trained NN can capture varied patterns)
Real Estate Appraiser is not applying some set formula, but balancing her experience and knowledge of sale prices of similar housesher knowledge about housing prices is not static...fine tuning her calculation to fit the latest data
241-320 Design Architecture & Engineering for Intelligent System
Loan Prospector ( )
A Neural Network is like a black box that knows how to process inputs to create a useful output. The calculation is quite complex and difficult to understand, yet the results are often useful
241-320 Design Architecture & Engineering for Intelligent System
Ability to generalize
i.e. produce reasonable outputs for inputs it has not been taught how to deal with
10
11
12
A Biological neuron
Dendrits cell and nucleus Dendrits: (Input) Getting other activations Axon: (Output ) forward the activation (from 1mm up to 1m long) Synapse: transfer of activation: to other cells, e.g. Dendrits of other neurons a cell has about 1.000 to 10.000 connections to other cells Cell Nucleus: (processing) evaluation of activation
13
w1i w2i
...
wji
net i w ji o j
acti f act (neti , i )
Dendrits cell and nucleus
net w act fact
j
oi f out (acti )
oi
: input from the network : weight of a connection : activation : activation function : bias/threshold : output function (mostly ID) : output 14
fout o
Abstraction
Dendrits: weighted (real number) connections Axon: output: real number Synapse: --(identity: output is directly forwarded) Cell nucleus: unit contains simple functions input = (many) real numbers processing = activation function output = real number (~activation)
241-320 Design Architecture & Engineering for Intelligent System
15
Artificial Neuron
16
Loan Prospector
( )
17
18
19
20
21
learning examples
Network
changing
network parameters
22
Unsupervised Training
Only supplies inputs
The neural network adjusts its own weights so that similar inputs should generate the similar outputs The network identifies the patterns and differences in the inputs without any external assistance
241-320 Design Architecture & Engineering for Intelligent System
23
Format
Frequency distribution (60 bins) Analogy: cochlea
241-320 Design Architecture & Engineering for Intelligent System
24
Network architecture
Feed forward network
60 input (one for each frequency bin) 6 hidden 2 output (0-1 for Steve, 1-0 for David)
25
David
26
David
0.73 0.55
27
Calculate error
Steve
0.43 0 0.26 1 = 0.43 = 0.74
David
0.73 1 0.55 0 = 0.27 = 0.55
28
29
30
0.01 0.99
David
0.99 0.01
31
Summary: Network has learnt to generalise from original data Networks with different weight settings can have same functionality Trained networks concentrate on lower frequencies Network is robust against non-functioning nodes
241-320 Design Architecture & Engineering for Intelligent System
32