Documentos de Académico
Documentos de Profesional
Documentos de Cultura
x1
w1
1 w1
slope =
y w2
2 w2
w2
0 2
x2
W1=1, w2=2, 2
Learning and Generalization
Classification: The ability to assign an input observation to a
category
Learning is a relatively permanent change in behaviour brought
about by experience.
Learning: The network must learn decision surfaces from a set of
training patterns so that these training patterns are classified
correctly.
Generalization: After training, the network must also be able to
generalize, i.e.correctly classify test patterns it has never seen
before.
Usually we want our neural networks to learn well, and also to
generalize well.
Sometimes, the training data may contain errors (e.g. noise in the
experimental determination of the input values, or incorrect
classifications). In this case, learning the training data perfectly
may make the generalization worse. There is an important
tradeoff between learning and generalization that arises quite
generally.
Blue lines show the decision boundaries of two neural networks to solve a
two class classification problem. Which is a better neural network?
x2
2 1
x1
Generalization in Classification
Generalization in Function Approximation
Training a Neural Network
-1
x1
1
3
1
-1 1
x2
1 1
1
-4 -2.5
x3=1
x1-x2>0
3-x1>0
2
x1+x2-4>0
x1-x2=0 x1+x2-4=0
1 2 3
x1
Illustration of some possible decision boundaries which can
be generated by networks having threshold activation
functions and various numbers of layers (if activation
function is step function)
Design a single output two layer network which classifies
the shaded region in Fig. from the other region.
(1,3)
(3, 2)
(1,1)
The following general learning rule is adopted in neural network studies
The weight increases in proportion to the product of input x
w r x
and learning signal r
x1=[1 0 -2 -1]';
where η is called learning rate.
w1=[-1 2 0 .5]';
For perceptron r =(t-o) t=target
net1=w1'*x1
shown in Fig. 1. x1=[ 1 0 -2 -1]t and x2=[ -1 2 0 -1]t . The w2=w1+0.1*(1- sign(net1))*x1
target for x1 is 1 and for x2 is -1. The initial weight vector w2 = -0.8000
is w=[ -1 2 0 0.5]t Apply perceptron learning rule to 2.0000
find the weight w3 after one epoch. η = 0.1. -0.4000
0.3000
Fig. 1 x2=[-1 2 0 -1]';
w1
net2=w2'*x2
w2 net2 = 4.5000
w3=w2+0.1*(-1-sign(net2))*x2
w3 w3 = 0.6000
1.6000
w4 -0.4000
0.5000