Backpropagation algo
Click here to load reader
-
Upload
not-yet-working-im-still-studying- -
Category
Engineering
-
view
49 -
download
2
Transcript of Backpropagation algo
![Page 1: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/1.jpg)
BACKPROPAGATION ALGORITHM
BY:Amit kumar
![Page 2: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/2.jpg)
CONTENTS:
1.Introduction2. Example of Backpropagation4.Algorithm6. Advantages7.Disadvantages8. Application9. Conclusion
Blackcollar4/23/2015 2
![Page 3: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/3.jpg)
INTRODUCTION
Backpropagation, an abbreviation for "backward propagation of errors" is a common method of training artificial neural networks.
The method calculates the gradient of a loss function with respects to all the weights in the network.
The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the loss function.
Blackcollar4/23/2015 3
![Page 4: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/4.jpg)
Backpropagation requires a known, desired output for each input value in order to calculate the loss function gradient.
The backpropagation learning algorithm can be divided into two phases:
Propagation
Weight update
In Propagation neural network using the training pattern target in order to generate the deltas of all
output and hidden neurons.
Multiply its output delta and input activation to get the gradient of the weight.
Blackcollar4/23/2015 4
![Page 5: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/5.jpg)
EXAMPLE OF BACKPROPAGATION
Inputs xi arrive through pre-connected path
Input is modeled using real weights wi
The response of the neuron is a nonlinear function f of its weighted inputs
Blackcollar4/23/2015 5
![Page 6: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/6.jpg)
Learning is the process of modifying the weights in order to produce a network that performs some function.
Blackcollar4/23/2015 6
![Page 7: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/7.jpg)
ALGORITHMThe following steps is the recursive definition of
algorithm:Step:-1.Randomly choose the initial weights.
2.For each training pattern apply the inputs to the network.
3.Calculate the output for every neuron from the inputlayer, through the hidden layer(s), to the output layer.
4.Calculate the error at the outputs:Use the output error to compute error signals for pre-output layers.
ErrorB= OutputB(1-OutputB) (TargetB-OutputB)Blackcollar4/23/2015 7
![Page 8: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/8.jpg)
use the error signals to compute weight adjustments.
W+AB = WAB + (ErrorB x OutputA)
Apply the weight adjustments.
Where
W+AB is New weight and WAB is initial weight
Output(1-Output)- the Sigmoid Function .
Blackcollar4/23/2015 8
![Page 9: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/9.jpg)
Advantages
Backpropagation has many advantages:-
It is fast, simple and easy to program.
It has no parameters to tune (except for the number of input) .
This is a shift in mind set for the learning-system designer instead of trying to design a learning algorithm that is accurate over the entire space
It requires no prior knowledge about the weak learner and so can be flexible.
Blackcollar4/23/2015 9
![Page 10: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/10.jpg)
Disadvantages
Disadvantages are:-
The actual performance of Backpropagation on a particular problem is clearly dependent on the input data.
Backpropagation can be sensitive to noisy data and outliers.
Fully matrix-based approach to backpropagation over a mini-batch .
Blackcollar4/23/2015 10
![Page 11: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/11.jpg)
Application
Mapping character strings into phonemes so they can be pronounced by a computer.
Neural network trained how to pronounce each letter in a word in a sentence, given the three letters before and three letters after it in a window
In the field of Speech Recognition.
In the field of Character Recognition.
In the field of Face Recognition.
Blackcollar4/23/2015 11
![Page 12: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/12.jpg)
Conclusion
The backpropagation algorithm normallyconverges reasonably fast However, the actualspeed depends very much on the simulationparameters on the initial weight values.
Blackcollar4/23/2015 12
![Page 13: Backpropagation algo](https://reader038.fdocuments.us/reader038/viewer/2022100519/55a96ab31a28ab576e8b47f1/html5/thumbnails/13.jpg)
Thank you !
Blackcollar4/23/2015 13