0% found this document useful (0 votes)
86 views14 pages

Solution To Credit Assignment Problem in MLP. Rumelhart, Hinton and Relating To Economics)

Backpropagation is an algorithm used to train multilayer perceptrons and calculate gradients for neural networks. It has two phases: the forward pass and the backward pass. In the forward pass, data is fed through the network to calculate outputs. In the backward pass, error is propagated back through the network to update weights using gradient descent, reducing error at each step. Weights are updated layer by layer from the output toward the input to minimize overall network error. Repeated iterations of this process are required to fully train the network on large datasets.

Uploaded by

Rogelio Cañas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
86 views14 pages

Solution To Credit Assignment Problem in MLP. Rumelhart, Hinton and Relating To Economics)

Backpropagation is an algorithm used to train multilayer perceptrons and calculate gradients for neural networks. It has two phases: the forward pass and the backward pass. In the forward pass, data is fed through the network to calculate outputs. In the backward pass, error is propagated back through the network to update weights using gradient descent, reducing error at each step. Weights are updated layer by layer from the output toward the input to minimize overall network error. Repeated iterations of this process are required to fully train the network on large datasets.

Uploaded by

Rogelio Cañas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 14

Backpropagation learning algorithm ‘BP’

Solution to credit assignment problem in MLP. Rumelhart, Hinton and


Williams (1986) (though actually invented earlier in a PhD thesis
relating to economics)

BP has two phases:

Forward pass phase: computes ‘functional signal’, feed forward


propagation of input pattern signals through network

Backward pass phase: computes ‘error signal’, propagates


the error backwards through network starting at output units
(where the error is the difference between actual and desired
output values)
1
Conceptually: Forward Activity -
Backward Error

2
Forward Propagation of Activity
• Step 1: Initialise weights at random, choose a
learning rate η
• Until network is trained:
• For each training example i.e. input pattern and
target output(s):
• Step 2: Do forward pass through net (with fixed
weights) to produce output(s)
– i.e., in Forward Direction, layer by layer:
• Inputs applied
• Multiplied by weights
• Summed
• ‘Squashed’ by sigmoid activation function
• Output passed to each neuron in next layer
– Repeat above until network output(s) produced
3
Step 3. Back-propagation of error
• Compute error (delta or local gradient) for each
output unit δ k
• Layer-by-layer, compute error (delta or local
gradient) for each hidden unit δ j by backpropagating
errors (as shown previously)

Step 4: Next, update all the weights Δwij


By gradient descent, and go back to Step 2
 The overall MLP learning algorithm, involving
forward pass and backpropagation of error
(until the network training completion), is
known as the Generalised Delta Rule (GDR),
or more commonly, the Back Propagation
(BP) algorithm
4
‘Back-prop’ algorithm summary
(with Maths!) (Not Examinable)

5
‘Back-prop’ algorithm summary
(with NO Maths!)

6
MLP/BP: A worked example

7
Worked example: Forward Pass

8
Worked example: Forward Pass

9
Worked example: Backward Pass

10
Worked example: Update Weights
Using Generalized Delta Rule (BP)

11
Similarly for the all weights wij:

12
Verification that it works

13
Training
• This was a single iteration of back-prop
• Training requires many iterations with many
training examples or epochs (one epoch is
entire presentation of complete training set)
• It can be slow !
• Note that computation in MLP is local (with
respect to each neuron)
• Parallel computation implementation is also
possible

14

You might also like