Code Monkey home page Code Monkey logo

digit-recognizer's Introduction

digit-recognizer

Neural Networks for Kaggle MNIST Classification tutorial. Original dataset contains 70000 28x28 images, Kaggle splits them into 32000 training set and 28000 test set, what results in lower classification accuracy than those given on site.

Networks

NN

Layer Dimensions
Input (100, 784)
Batch Normalization
PRelu 800
Dropout 0.5
Batch Normalization
PRelu 400
Dropout 0.5
Softmax 10

CNN

Layer Dimensions
Input (100,28,28,1)
Batch Normalization
Convolution (5,5,1,20)
Batch Normalization
PRelu
Max Pool (1,2,2,1)
Convolution (5,5,20,40)
Batch Normalization
PRelu
Max Pool (1,2,2,1)
Batch Normalization
Fully Connected PRelu 1600
Dropout 0.2
Batch Normalization
Fully Connected PRelu 400
Dropout 0.2
Softmax 10

Useful links

digit-recognizer's People

Contributors

dgawlik avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.