SasankYadati
Masters in Computer Science at CMI. Previously Software Engineer at Microsoft.
MicrosoftChennai
Pinned Repositories
8puzzle
A sliding block puzzle, whose solution is found using A* Search.
Adversarial-Attacks-in-Machine-Learning
A brief study on Adversarial Attacks and python scripts to generate and study them.
aima-python
Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
CS325-Artificial-Intelligence
Programs from CS325
FrozenLake-DP
Solving Finite MDPs using Dynamic Programming
Guns-Dataset
The repository contains labelled images of guns taken from various sources.
interpretability-in-neural-networks
Compare traditional neural networks with self explaining neural networks in terms of performance and interpretability.
kArmedBandit
Custom environments for K-Armed Bandit built using OpenAI's Gym
mech-interp
where I learn and explore mechanistic interpretability of transformers
wright-fisher-population-genetics-simulation
Population simulation of Wright-Fisher model using numpy
SasankYadati's Repositories
SasankYadati/Adversarial-Attacks-in-Machine-Learning
A brief study on Adversarial Attacks and python scripts to generate and study them.
SasankYadati/mech-interp
where I learn and explore mechanistic interpretability of transformers
SasankYadati/3Blue1Brown.com
SasankYadati/competitive-programming
SasankYadati/deception-detection
SasankYadati/einops-tutorial
SasankYadati/EPIJudge
EPI Judge - Preview Release
SasankYadati/Explore-LLMs
SasankYadati/fsdl-text-recognizer-2022-labs
SasankYadati/gpu-programming
SasankYadati/haskell-programming
SasankYadati/Interactive-Theorem-Proving-in-Coq
SasankYadati/ioi-replication
SasankYadati/keras
Deep Learning for humans
SasankYadati/llm-agents-uplifting
SasankYadati/llms-training-finetuning
SasankYadati/makemore-tutorial
SasankYadati/micrograd-makemore
SasankYadati/mini-gpt-from-scratch
SasankYadati/minitorch
Develop a mini pytorch
SasankYadati/NEKO
In Progress Implementation of a Generalist Multimodal model capable of image, text, RL and Robotics tasks
SasankYadati/omnisafe
OmniSafe is an infrastructural framework for accelerating SafeRL research.
SasankYadati/policy-gradient-rl
SasankYadati/prog-synth-basic
SasankYadati/programming-parallel-processors
SasankYadati/Reproducing-DQN
SasankYadati/RL-Gridworld-and-CartPole
SasankYadati/sasankyadati.github.io
SasankYadati/tokenizer
SasankYadati/wmdp
WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.