About

HyperQuest

HyperQuest mimics the hyperparameter tuning app from Stanford University, CS231n. HyperQuest is a web-app designed for beginners in Machine Learning to easily get a proper intuition for choosing the right hyperparameters. This is initially an extremely daunting task because not having proper hyperparameters leads to the models breaking down.

If you like this project, please give me a ⭐️ on GitHub

Instructions

  • You will be provided a specific dataset. Your goal is to train a neural network for classification on the dataset, and obtain the highest validation accuracy that you can

  • In the first stage, you will choose the initial network configuration

  • In the second stage, you will monitor the training process and have the option of adjusting hyperparameters at every epoch

Stacks Image 22

HyperQuest

Author

Stacks Image 36
Stacks Image 38

I'm Bingcheng HU, a student at New York University.

My research interests are machine learning, computer vision, and natural language processing.

ORCID iD: 0000-0002-8696-0971 Email: bingcheng@nyu.edu

Thanks

  • CS231n: Convolutional Neural Networks for Visual Recognition (Stanford University)
  • plotly.js
  • icons8.com

Useful references