Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

31
yright R. Weber Neural Networks INFO 629 Dr. R. Weber

Transcript of Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Page 1: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Neural Networks

INFO 629 Dr. R. Weber

Page 2: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

~= 2nd-5th week

training vision

the evidence

Page 3: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

the evidence

~= 2nd-5th week

training vision

10

Page 4: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

the evidence

~= 2nd-5th week

training vision

10

Page 5: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

the evidence

~= 2nd-5th week

training vision

Page 6: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

NN: model of brains

input output

neuronssynapses

electric transmissions:

Page 7: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Elements

• input nodes• output nodes• links• weights

Page 8: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

terminology

• input and output nodes (or units) connected by links

• each link has a numeric weight

• weights store information

• networks are trained on training sets (examples) and after are tested on test sets to assess networks’ accuracy

• learning/training takes place as weights are updated to reflect the input/output behavior

Page 9: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

The trainingOutput=Step(w f )

learning takes place as weights are updated to reflect the input/output behavior

=> mammal (1)=> bird (0)

0 1 1

4 legs flies eggs

i=1

i=2

i=3

j=1 j=2 j=3

ij

0 0 0

0 0 0

0 0 0

1 0 0

1 0 0

1 0 0

1 0 0

1 0 0

1 1 1

1 0 0

1 1 1

1 1 1

Goal minimize error between representation of the expected and actual outcome

20

ij

Page 10: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

The concept i

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

1 Yes, 0 No

=> mammal1 1 0

Page 11: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

The concept ii

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

=> mammal1 1 0

1 Yes, 0 No

Page 12: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

The learning i

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

=> mammal1 1 0

0.5 0.5 0.5

1 Yes, 0 No

Page 13: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

=> mammal1 1 0

0*0.5+1*0.5+1*0.5= 1

1*0.5+0*0.5+0*0.5= 0.5

1*0.5+1*0.5+0*0.5= 1Goal is to have weights that recognize different representations of mammals and birds as such

0.5 0.5 0.5

The learning ii

Page 14: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

=> mammal1 1 0

0*0.5+1*0.5+1*0.5= 1

1*0.5+0*0.5+0*0.5= 0.5

1*0.5+1*0.5+0*0.5= 1Suppose we want bird to be greater 0.5 and mammal to be equal or less than 0.5

0.5 0.5 0.5

The learning iii

Page 15: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

=> mammal

=> bird0 1 1

4 legs flylayeggs

1 0 0

=> mammal1 1 0

0*0.25+1*0.25+1*0.5= 0.75

1*0.25+0*0.25+0*0.5= 0.25

1*0.25+1*0.25+0*0.5= 0.5Suppose we want bird to be greater 0.5 and mammal to be equal or less than 0.5

0.25 0.25 0.5

The learning iv

Page 16: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

NN demo…..

Page 17: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Characteristics

• NN implement inductive learning algorithms (through generalization) therefore, it requires several training examples to learn;

• NN do not provide an explanation or a rule telling why the task performed the way it was;

• uses data rather than explicit knowledge; • Classification (pattern recognition), clustering,

diagnosis, optimization, forecasting (prediction), modeling, reconstruction, routing;

Page 18: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

NN Parameters• Number of hidden layers,• Randomly initialization of the weights• Error, threshold• Adjustment rate for weights fixed or variable

• Optimal parameters are determined empiricallyA. Abraham and B. Nath, “Hybrid Heuristics for

Optimal Design of Neural Nets,” in Proceedings of the Third International Conference on Recent Advances in Soft Computing, R. John and R. Birkenhead, Eds. Germany: Springer Verlag, 2000, pp. 15-22.

Page 19: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Network Topology: Feedforward & Feedback

• Feedforward– connections between units do not form cycles– produce a response to an input quickly– can be trained using a wide variety of efficient

conventional numerical methods

• Feedback (recurrent NN)– connections between units form cycles– Takes a long time before it produces a response– more difficult to train than feedforward

Page 20: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

• Feedforward– Linear, Perceptron, Adaline , Higher Order,

Functional Link, MLP: Multilayer perceptron, Backpropagation, Cascade Correlationm, Quickprop, RPROP , Radial Basis Function networks, OLS: Orthogonal Least Squares, CMAC: Cerebellar Model Articulation Controller, Classification only, LVQ: Learning Vector Quantization, Kohonen, PNN: Probabilistic Neural Network, GNN: General Regression Neural Network

Page 21: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

• Feedback – BAM: Bidirectional Associative Memory,

Boltzman Machine, Recurrent time series, Backpropagation through time , FIR: Finite Impulse Response, Real-time recurrent network, Recurrent backpropagation, TDNN: Time Delay NN

Page 22: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Where are NN applicable?

• Where they can form a model from training data alone;

• When there may be an algorithm, but it is not known, or has too many variables;

• There are enough examples available• It is easier to let the network learn from

examples• Other inductive learning methods may not be

as accurate

Page 23: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Applications (i)• predict movement of stocks, currencies, etc.,

from previous data;• to recognize signatures made (e.g. in a bank)

with those stored;• Classify medical imaging e.g., ECG signal, X

Rays, MRIs• classify the state of aircraft engines (by

monitoring vibration levels and sound, early warning of engine problems can be given; British Rail have been testing an application to diagnose diesel engines;

Page 24: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Applications (ii)• Pronunciation (rules with many exceptions);• Handwritten character recognition

(network w/ 200,000 is impossible to train, final 9,760 weights, used 7300 examples to train and 2,000 to test, 99% accuracy)

• ATR automated target recognition, distinguish threatening from non threatening targets;

• Learn brain patterns to control and activate limbs as in the “Rats control a robot by thought alone” article

• Credit assignment

Page 25: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Applications (iii)• Optimization (max,min) and routing (min

distances) problems • Modeling e.g., create model of input

vs.output analysis of software programs to work as an oracle of predicted output

• Reconstruction to produce clean versions of noisy patterns by matching the closest training pattern to input pattern

• Clustering

Page 26: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

CMU Driving ALVINNhttp://www.ri.cmu.edu/projects/project_160.html

• learns from human drivers how to steer a vehicle along a single lane on a highway

• ALVINN is implemented in two vehicles equipped with computer-controlled steering, acceleration, and braking

• cars can reach 70 m/h with ALVINN• programs that consider all the problem

environment reach 4 m/h only

Page 27: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eberWhy using NN for the driving task?

• there is no good theory of driving, but it is easy to collect training samples

• training data is obtained with a human* driving the vehicle–5min training, 10 min algorithm runs

• driving is continuous and noisy• almost all features contribute with useful

information*humans are not very good generators of training instances when they behave too regularly without making mistakes

Page 28: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

• INPUT:video camera generates array of 30x32 grid of input nodes

•OUTPUT: 30 nodes layer corresponding to steering direction

•vehicle steers to the direction of the layer with highest activation

the neural network

Page 29: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Genetic algorithms (i)

• learn by experimentation• based on human genetics, it originates new

solutions • representational restrictions• good to improve quality of other methods

e.g., search algorithms, CBR• evolutionary algorithms (broader)

Page 30: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Genetic algorithms (ii)

• requires an evaluation function to guide the process• population of genomes represent possible solutions• operations are applied over these genomes• operations can be mutation, crossover• operations produce new offspring• an evaluation function tests how fit an offspring is • the fittest will survive to mate again

Page 31: Copyright R. Weber Neural Networks INFO 629 Dr. R. Weber.

Copy

right

R. W

eber

Genetic Algorithms (iii)

• http://ai.bpa.arizona.edu/~mramsey/ga.html You can change parameters

• http://www.rennard.org/alife/english/gavgb.html Steven Thompson presented