A research proposal to improve offline learning using novelty driven policy distillation

(Research Idea) Transformer-Based Multi-Task RL with Policy Distillation

A brief overview covering implicit bias and incremental learning

The Great Mystery of Deep Networks- Generalization

Building a recommendation system for online dating

Second pass notes on Ian Goodfellow's Deep Learning textbook

Select bonus challenge problems I solved in Professor Srebo's TTIC 31120 Statistical Learning Theory.

Discrete diffusion models for sudoku and improving generation with guidance

Naive idea for diffusion guidance with non-differentiable guidance function

Background on discrete diffusion and a proposed diffusion method for inverse protein folding

Proposed method of quantifying groundedness of LLM output through data augmentations

Proposed method of quantifying uncertainty of LLMs

Learning and Game Theory final project report on an ensemble based strategy for stock trading

How to build a connect 4 player using minimax algorithm (with alpha beta pruning and heuristic search)

Recreated a game that I once played on a flip phone as a kid - this time with better facial detection.