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.
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
HyperQuest
Author
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