LucaGatt22 / MLP-neural-network Public

generated from github/codespaces-blank

Notifications You must be signed in to change notification settings
Fork 0
Star 0

A Multi Layer Perceptron created to calculate XOR (eXclusive OR) on 5 inputs

0 stars 0 forks Branches Tags Activity

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
graphs before randomising trainingSet		graphs before randomising trainingSet
graphs		graphs
5XOR.csv		5XOR.csv
BadFactsVsEpochGraph - 4 hidden layer neurons.jpg		BadFactsVsEpochGraph - 4 hidden layer neurons.jpg
BadFactsVsEpochResults.csv		BadFactsVsEpochResults.csv
README.md		README.md
assign neural network.py		assign neural network.py

Repository files navigation

Multi Layer Perceptron - Neural Network

A Multi Layer Perceptron created to calculate XOR (eXclusive OR) on 5 inputs.

Definitions

Bad facts are those where the actual output calculated by the neural netowrk is different from the expected output.
Good facts - negation of bad facts i.e. actual = expected

Refer to this link for more information about neural networks and MLPs.

File Structure:

5XOR.csv - the XOR entries/rows/combinations for 5 inputs with their outputs
assign neural network.py is the only program.
BadFactsVsEpochResults.csv is an example of the results exported to a spreadsheet.
The rest are many graphs which are images.
- Graph data is affected by how the program is written, for example if the order of XOR entries is randomised. In fact, there are 2 folders, one named graphs before randomising trainingSet and graphs.