Giter Club home page Giter Club logo

semi-supervised-learning's Introduction

semi-supervised-learning

Considered 1000 labeled datapoints from MNIST with 100 labeled samples from each digit. Used the rest of the training images as unlabeled data. Trained the sparse autoencoder with p=0.1 and extracted the hidden representations for these labeled samples to get a matrix with dimensions [D ร— m] = [200 ร— 1000].

1] Train a softmax classifier with these feature representations to classify the digits. Combined the encoder and the softmax classifier to create a classifier with network dimensions [784, 200, 10].

2] Created another fully connected network with same dimensions [784, 200, 10] and initialize it with random values.Trained it with 1000 labeled samples from MNIST.

Using these two networks, computed the classification accuracies for the unlabeled data.To compare the performance between them, in this competition sparse-autoencoder network[1] won.

how to run the code

  1. Clone the project
  2. run 'download_mnist.sh'
  3. run 'sparseae_ssl.py'

semi-supervised-learning's People

Contributors

vivekamin avatar

Stargazers

 avatar  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.