Giter VIP home page Giter VIP logo

overparametrized-nn-experiments's Introduction

Experiments for the Lazy vs Rich regimes of shallow ReLU neural networks

  • Experiment 1: Effect of overparametrization
    • Final settings:
      • inputDim = 3
      • hiddenSize = 3
      • overFactor = 1, 100
      • dataSize = 48
      • LR = 0.33333
      • epochs = 2000
      • seed = 0
  • Experiment 2: Effect of initialization scale
    • Final settings:
      • inputDim = 3
      • hiddenSize = 3
      • overFactor = 1000
      • dataSize = 48
      • LR = 0.01
      • target = 1e-8
      • seed = 100
      • scales = 0.01,0.03,0.1,0.32,1,3,10,14
  • Experiment 3: Visualizing weights (non-Lazy vs Lazy regime)
    • Final settings:
      • inputDim = 3
      • hiddenSize = 3
      • overFactor = 33
      • dataSize = 48
      • LR = 0.25
      • target = 1e-8
      • seed = 100
      • scales = 0.01,3
  • Experiment 4: Visualizing learned function vs 2D training samples
    • Final settings:
      • inputDim = 2
      • hiddenSize = 3
      • overFactor = 33
      • dataSize = 48
      • LR = 0.25
      • target = 1e-8
      • seed = 100
      • scales = 0.01,3

overparametrized-nn-experiments's People

Contributors

berktinaz avatar

Watchers

James Cloos avatar avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.