Discover @clam004 Open Source projects

Carson Lam (@clam004)

clam004

Stars
405
Global Rank 69,477 (Top 3 %)
Followers 48
Following 32
Registered over 11 years ago
Most used languages

Jupyter Notebook
83.3 %

HTML
8.3 %

Python
8.3 %
Location 🇺🇸 United States
Country Total Rank 17,286
Country Ranking

Jupyter Notebook
508

intro_continual_learning

This is a tutorial to connect the fundamental mathematics to a practical implementation addressing the continual learning problem of artificial intelligence

Jupyter Notebook

RL-Chat-pytorch

reinforcement learning on a encoder-decoder GRU for chatbot dialogue generation

Jupyter Notebook

minichatgpt

annotated tutorial of the huggingface TRL repo for reinforcement learning from human feedback connecting equations from PPO and GAE to the lines of code in the pytorch implementation

Jupyter Notebook

chat-transformer

A chatbot using the Vaswani transformer as it's sequence-to-sequence module

Jupyter Notebook

unsupervised-speech-representation-learning

This is a intuitive explanation of Representation Learning with Contrastive Predictive Coding using code provided by jefflai108 that uses CPC to learn representations of sound files for the purpose of speech recognition

Jupyter Notebook

triton-ft-api

tutorial on how to deploy a scalable autoregressive causal language model transformer using nvidia triton server

va-irl

Variational Adversarial Inverse Reinforcement Learning

Jupyter Notebook

proximalpolicyoptimization

basic implementation of PPO reinforcement learning algorithm on lunar lander

Jupyter Notebook

adaptive-computation-time

The notebook connects the formulas used in the paper to the code that implements those formulas by implementing a training pipeline on a small but meaningful dataset

General-Deep-Learning-NLP-Classifier

Template for multi-class classification with variable length sequences using Gated Recurrent Units

Jupyter Notebook

xgboost-tutorial

detailed tutorial on xgboost

Jupyter Notebook

max_ent_irl

Maximum Entropy Inverse Reinforcement Learning - notes and tutorial for IRL using the principle of maximum entropy

Jupyter Notebook