Yash Bonde Blog

Musings of a bored Engineer

This is the home page for all the blogs that I have written over the time. I prefer to write very long form or detailed kind of articles here while some of the smaller and edited versions are available on Medium. All of my posts on my site are given below, if you like something feel free to share on the social. Reach out to me on Linkedin or Instagram. The cards with same gradient belong to the same group of blogs.
Cheers!

23.04.2021 Notes and Results of RNN-Sim How fast can we run Language Models on CPUs Interactive graphs for Experiments RNN-Sim 21.11.2020 Chess Engine - (Part 1) Pretraining a network on 18.6 lakh moves This is first in a series of blogs covering this project. Covers building primary network and training. Some rant on Intelligence. 11.05.2020 Reading List on Neural Graph Execution Lets Call this Neural Algorithm Execution (NAE) Note of papers on graph neural networks learning "programs" 27.04.2020 Chapter 6: Temporal-Difference Learning Barto Sutton: Learning from Experiences minus the Complete Rollout Notes from the book Reinforcement Learning: An Introduction 23.04.2020 Practicing GraphNet Making a graphnet for drug multitask classification (PTC) Graphs are how we represent most of the data and neural networks should be able to read them 11.04.2020 Chapter 5: Monte Carlo Methods Barto Sutton: Learning from experience Notes from the book Reinforcement Learning: An Introduction 04.04.2020 Teaching Machines Rules and Algorithms Cellular Automata Learning Neural Network Can we teach neural network rules rather than them deciphering it 25.08.2019 Chapter 4: Dynamic Programming Barto Sutton: DP algorithms on known transitions Notes from the book Reinforcement Learning: An Introduction 14.07.2019 Chapter 3: Goals and Rewards Barto Sutton: Understanding MDPs Notes from the book Reinforcement Learning: An Introduction 31.05.2019 How to Read Textbooks Something I have been Applying Lately Quickly read your textbooks, especially if you have exams coming up 19.05.2019 Chapter 2: Multi-Armed Bandit Barto Sutton: Handling Exploitation vs. Exploration Notes from the book Reinforcement Learning: An Introduction 23.01.2019 Transfer Learning in RL using Generative Models Attempt at RoR 2.0 #5 OpenAI's RoR 2.0 (Requests for Research) has always been the benchmark... 08.01.2019 FLE Update #2 FLE- Freeciv Learning Environment In a previous post I wrote about the importance of developing the Freeciv Learning... 29.12.2018 Second in the Series of Musings A step in another direction With my previous post written well over 4 months ago from the date of this writing I talked about A.I. and it's types... 19.11.2018 Let’s go over a few things freeciv! Setting up the foundation right is the key to great development As I talked in my previous post, I have a keen interest in setting up a freeciv... 9.11.2018 Call for an Army of Be(a)sts! Pushing for a more democratized AI. Artificial Intelligence will be powered by three domains, a better understanding of natural languages, generative models learning...