Saumik Narayanan

  • Home
  • Blog
  • Projects
  • CV

Blog

Thoughts on my first NeurIPS

Yesterday, I finished my first ever NeurIPS conference. It was a great experience, as I got to present some of my recent work and get feedback, meet friends from around the country, learn about awesome research in many fields, and...

Read more

Using GPUs and JupyterLab on the WashU RIS Cluster

In this post, I'll give a step-by-step tutorial on how to get started running Deep Learning code using Pytorch, Tensorflow, and JupyterLab on the GPUs available in the WashU RIS cluster. Getting Access First, you will need to get access...

Read more

Visualizing Airline Routes and Hubs

You can jump straight to the interactive visualization here. Details on how I implemented this project is available in the Github repo.   Growing up, whenever my family used to take airplanes, I was always drawn to the airline route...

Read more

What every computer science major should know (to get an internship)

When a new student is starting their journey into the field of computer science, it can be hard to figure out which topics to learn first. In this post, I will give my opinionated review on what every computer science Read more…

By Saumik, 7 monthsJuly 8, 2022 ago

A Brief Guide to Maia

Over the last few months, I’ve been working on a research project to develop personalized training tools for chess players. For this post, I’m just going to describe Maia, the framework developed last year which all of our code and Read more…

By Saumik, 2 yearsMay 23, 2021 ago

Predicting Move Times in Chess – Final Report

Summary For this project, I analyzed methods to model the aleatoric and epistemic uncertainty of a neural network model for predicting the amount of time that a human player will use for a given move in a chess position. Dataset Read more…

By Saumik, 2 yearsMay 3, 2021 ago

Predicting Move Times in Chess – Status Update

Summary For this project, I am comparing the abilities of Bayesian and non-Bayesian neural networks as a predictor for how much time a chess player will use to make their move in a certain chess position, taking into account the Read more…

By Saumik, 2 yearsApril 4, 2021 ago

Predicting Move Times in Chess – Intro

Problem During a chess game, players are constantly making decisions and evaluating the current state to increase their odds of winning. The process of analyzing positions is a problem that AI has already achieved superhuman performance on, and the use Read more…

By Saumik, 2 yearsMarch 14, 2021 ago

Working Harder, not Smarter in Pacman

Introduction In my AI class this semester, we have a 3-part course project based on the Berkeley CS118 Pacman Project. The first part of this project was due last week, and we were asked to implement some straightforward search algorithms Read more…

By Saumik, 2 yearsFebruary 28, 2021 ago

A Brief Guide to Stockfish NNUE

In my last two posts, I gave brief overviews to two of the more established paradigms for chess engines, represented by Stockfish and AlphaZero. In this post, I will go over the latest engine on the block – Stockfish NNUE. Read more…

By Saumik, 2 yearsJanuary 24, 2021 ago

Posts navigation

1 2 … 4 Next
Recent Posts
  • Thoughts on my first NeurIPS December 4, 2022
  • Using GPUs and JupyterLab on the WashU RIS Cluster November 17, 2022
  • Visualizing Airline Routes and Hubs October 31, 2022
  • What every computer science major should know (to get an internship) July 8, 2022
  • A Brief Guide to Maia May 23, 2021
  • Predicting Move Times in Chess – Final Report May 3, 2021
  • Predicting Move Times in Chess – Status Update April 4, 2021
  • Predicting Move Times in Chess – Intro March 14, 2021
  • Working Harder, not Smarter in Pacman February 28, 2021
  • A Brief Guide to Stockfish NNUE January 24, 2021
Archives
  • December 2022 (1)
  • November 2022 (1)
  • October 2022 (1)
  • July 2022 (1)
  • May 2021 (2)
  • April 2021 (1)
  • March 2021 (1)
  • February 2021 (1)
  • January 2021 (4)
  • December 2020 (4)
  • November 2020 (4)
  • October 2020 (7)
  • September 2020 (3)
  • June 2020 (1)
  • March 2020 (1)
  • October 2019 (1)
  • July 2019 (1)
  • June 2019 (2)
  • Facebook
  • LinkedIn
  • Twitter
  • Instagram
Hestia | Developed by ThemeIsle