Skip to content

This project is the end of one of the Data-Science branch at 42 Paris. It requires the defendant to implement his own Multilayer Perceptron using 5 different layers. And then predicting with it on given data

License

Notifications You must be signed in to change notification settings

SpenderJ/Multilayer-Perceptron

Repository files navigation

Multilayer-Perceptron

42 2020-Data-Science Project. Implementation of your own Neural Network system.

Multilayer-Perceptron

Multilayer-Perceptron is an advanced project and the end of one the algorithmic/artificial intelligence branch at 42 Paris. The goal of this project is to learn how does a Neural Network system works. Then you are asked to create your own Neural Network system Answering certain requirements such as at least 2 hidden layers, a softmax layer on the output...

Running the project

The project mark is : [Not delivered yet]

To test the project, you will have to first of all clone the repo. 2 different python scripts are waiting for you to launch. Just don't forget to download the different libraries needed, the downloading of the data will be automatically done, if you don't have downloaded it already.

python train.py

python predict.py

Contributing

Jules Spender

Authors

See also the list of contributors who participated in this project.

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

  • Project Management
  • Python
  • Documentation
  • Neural Network Implementation
  • Layers in objects

About

This project is the end of one of the Data-Science branch at 42 Paris. It requires the defendant to implement his own Multilayer Perceptron using 5 different layers. And then predicting with it on given data

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages