The Adaline Learning Algorithm
The Adaline Learning Algorithm
The Adaline Learning Algorithm
i1
i2
Adjust
weights
w0 + w1i1 + + wnin
Output
Compare with
desired value
class(i) (1 or -1)
Neural Networks
Lecture 7: Perceptron Modifications
Neural Networks
Lecture 7: Perceptron Modifications
2(d j net j )
(net j )
wk
wk
n
2(d j net j )
wl il , j
wk l 0
Neural Networks
Lecture 7: Perceptron Modifications
: 2(d j net j )i j
E
wn
Neural Networks
Lecture 7: Perceptron Modifications
w (d j net j )i j
Longer input vectors result in greater weight changes,
which can cause problems if there are extreme
differences in vector length in the training set.
Widrow and Hoff (1960) suggested the following
modification of the learning rule:
w (d j net j )
September 28, 2010
ij
|| i j ||
Neural Networks
Lecture 7: Perceptron Modifications
Multiclass Discrimination
Often, our classification problems involve more than
two classes.
For example, character recognition requires at least
26 different classes.
We can perform such tasks using layers of
perceptrons or Adalines.
Neural Networks
Lecture 7: Perceptron Modifications
Multiclass Discrimination
w11
w12
i1
o1
o2
i2
..
.
o3
in
w4n
o4
Multiclass Discrimination
Each perceptron learns to recognize one particular
class, i.e., output 1 if the input is in that class, and 0
otherwise.
The units can be trained separately and in parallel.
In production mode, the network decides that its current
input is in the k-th class if and only if ok = 1, and for all j
k, oj = 0, otherwise it is misclassified.
For units with real-valued output, the neuron with
maximal output can be picked to indicate the class of the
input.
This maximum should be significantly greater than all
other outputs, otherwise the input is misclassified.
September 28, 2010
Neural Networks
Lecture 7: Perceptron Modifications
Multilayer Networks
Although single-layer perceptron networks can
distinguish between any number of classes, they still
require linear separability of inputs.
To overcome this serious limitation, we can use multiple
layers of neurons.
Rosenblatt first suggested this idea in 1961, but he
used perceptrons.
However, their non-differentiable output function led to
an inefficient and weak learning algorithm.
The idea that eventually led to a breakthrough was the
use of continuous output functions and gradient
descent.
September 28, 2010
Neural Networks
Lecture 7: Perceptron Modifications
Multilayer Networks
The resulting backpropagation algorithm was
popularized by Rumelhart, Hinton, and Williams
(1986).
This algorithm solved the credit assignment
problem, i.e., crediting or blaming individual neurons
across layers for particular outputs.
The error at the output layer is propagated backwards
to units at lower layers, so that the weights of all
neurons can be adapted appropriately.
The gradient descent technique is similar to the
Adaline, but propagating the error requires some
additional computations.
September 28, 2010
Neural Networks
Lecture 7: Perceptron Modifications
10
Terminology
Example: Network function f: R3 R2
output vector
o1
o2
output layer
w2( 2, 4,1)
( 2 ,1)
1,1
hidden layer
w1(,11, 0)
w4(1,3, 0 )
input layer
x1
x2
input vector
x3
Neural Networks
Lecture 7: Perceptron Modifications
11