Forward Pass Computations through a Back-Propagation Neural ...

clangedbivalveAI and Robotics

Oct 19, 2013 (3 years and 11 months ago)

83 views

Procedure for Training a Child to Identify a Cat using 10,000
Example Cats

For Cat_index


1 to 10000


1. Show cat and describe catlike features (Cat_index)


2. Child adjusts biological neural network in response to

receiving the features of example cat Cat_index


3. Cat_index


Cat_index + 1

Procedure for Testing a Trained Child’s ability to Identify a
new Cat

1. Show new cat and describe catlike features

2. Child processes features with biological neural network in
response to receiving the features of new example cat

3. Output of biological neural network indicates weather or
not new example is a cat

Smoothing function for converting the output of a neuron into the range [0,1]

Forward Pass Computations through a Back
-
Propagation
Neural Network with three layers having 4, 6, and 8 nodes

INPUT input(1),input(2),input(3),input(4)

For i


1 to 6


middle_in (i)


0


For j


1 to 4



middle_in (i) < middle_in (i) + weight(j,i) * inp8ut (j)


middle_out (i)


Fermi (middle_in(i))


For k


1 to 8


output (k)

0


For i


1 to 6



output (k)


output (k) + weight (i,k) * middle_out (i)


INPUT known_true_value (k)


error (k)


known_true_value (k)


output (k)

General Procedure for training a neural network, then testing
it on new examples

INPUT known true values for each example

For i


1 to number_of_examples_in_input_set



INPUT numbers that measure values of input features for this example



INPUT known true classification values for this example





Do forward neural net computation to get outputs



Compute error by subtracting known true values from outputs



Set error_tolerance_threshold





Repeat until error tolerance <= error_tolerance_threshold





Do backpropagation for an epoch and adjust weights