Machine Learning
Machine Learning
Lecture 6
3
The biological neuron
• The pulses
generated by
the neuron
travels along
the axon as an
electrical wave.
• Once these
pulses reach
the synapses at
the end of the
axon open up
chemical
vesicles
exciting the
other neuron.
4
Neural Network
X1
W1
Inputs X2 W2 f Output
Wn
Xn
Neural Network
Application
04/23/25 8
Automated driving at 70 mph on
a public highway
Camera
image
30 outputs
for steering 30x32 weights
into one out o
4 hidden
four hidden
units
unit
30x32 pixels
as inputs 9
Neuron Model
• A neuron has more than one input x1, x2,..,xm
• Each input is associated with a weight w1,
w2,..,wm
• Neurons have also biases b as an additional
input component, This representation for the
bias is useful because bias terms can be
interpreted as additional weights
• The net input of the neuron is
n = w1 x1 + w2 x2+….+ wm xm + b
n wi xi b
Neuron output
y = f (n)
• f is called transfer function
Transfer Function
– Linear
– sigmoid
n wi xi b
Y= 1/(1+e^(-1.6)) = 0.832
Learning Rule
of the connections.
Inputs X2 W2 f Output
Wn
Xn
Perceptron
=f (wixi +b)
Perceptron Learning
Rule
W new = W old + (t-o) X
• Linearly separable:
– Can use a line (dotted) to separate +1 and –1
• Think of the line as representing the threshold
– Angle of line determined by two weights in perceptron
– Y-axis crossing determined by threshold
Linearly Separable
Functions