Title: CS621: Artificial Intelligence Lecture 17: Feedforward network (lecture 16 was on Adaptive Hypermedia: Debraj, Kekin and Raunak)
1CS621 Artificial IntelligenceLecture 17
Feedforward network(lecture 16 was on Adaptive
Hypermedia Debraj, Kekin and Raunak)
- Pushpak Bhattacharyya
- Computer Science and Engineering Department
- IIT Bombay
2Machine Learning Basics
- Learning from examples
- e1,e2,e3 are ve examples
- f1, f2, f3 are ve examples
3Classification of Learning Paradigms
Learning
Statistical
Knowledge Based
Learning From Analogy
Learning From Examples
Neural Networks
Learning From Examples
Decision Trees
4Example Loan Reliability Detection (Feature
Vector)
- Features for deciding if a person is reliable for
granting loan - Age Numerical
- Gender categorical
- Education categorical
- Salary numerical
- Family background categorical
- Loan history categorical
5Kolmogorov Theorem 1965
- (Informal Statement) A function (Yes/No) can be
computed by a 3-layer n/w of simple Yes/No
computing elements
63 Layer NN for XOR
XYXY
T 0.5
1
1
XY
XY
T 0.5
T 0.5
-1
-1
1
1
Y
X
7A popular universal data for testing learning
algorithms IRIS Data
Sepal Length Sepal Width Petal Length Petal Width Classes
5.1 3.5 1.4 0.2 setosa
4.9 3.0 1.4 0.2 setosa
6.3 2.9 5.6 1.8 virginica
6.9 3.1 4.9 1.5 versicolor
5.5 2.3 4.0 1.3 versicolor
5.7 2.8 4.1 1.3 versicolor
6.3 3.3 6.0 2.5 virginica
5.7 2.8 4.1 1.3 versicolor
6.3 3.3 6.0 2.5 virginica
8Machine Learning Basics cont..
- Training arrive at hypothesis h based on the
data seen. - Testing present new data to h test performance.
hypothesis
h
concept
c
9Feedforward Network
10Limitations of perceptron
- Non-linear separability is all pervading
- Single perceptron does not have enough computing
power - Eg XOR cannot be computed by perceptron
11Solutions
- Tolerate error (Ex pocket algorithm used by
connectionist expert systems). - Try to get the best possible hyperplane using
only perceptrons - Use higher dimension surfaces
- Ex Degree - 2 surfaces like parabola
- Use layered network
12Pocket Algorithm
- Algorithm evolved in 1985 essentially uses PTA
- Basic Idea
- Always preserve the best weight obtained so far
in the pocket - Change weights, if found better (i.e. changed
weights result in reduced error).
13XOR using 2 layers
- Non-LS function expressed as a linearly
separable - function of individual linearly separable
functions.
14Example - XOR
? Calculation of XOR
w21
w11
x1x2
x1x2
x1 x2 x1x2
0 0 0
0 1 1
1 0 0
1 1 0
Calculation of
x1x2
w21.5
w1-1
x2
x1
15Example - XOR
w21
w11
x1x2
1
1
x1x2
1.5
-1
-1
1.5
x2
x1
16Some Terminology
- A multilayer feedforward neural network has
- Input layer
- Output layer
- Hidden layer (assists computation)
- Output units and hidden units are called
- computation units.