Topic

PyTorch

A collection of 4 issues

Multi-Tenant Smart Locker Capacity Management with Deep Reinforcement Learning

A deeper look into multi-tenant smart locker capacity management proposing a Deep Reinforcement learning approach to overbooking, in order to maximize throughput while keeping failure rates low.

Policy Gradients: REINFORCE from Scratch

Deep dive into Policy Gradient methods, specifically REINFORCE deriving the mathematical foundations as well as the implementation from scratch.

Running PyTorch Models for Inference at Scale using FastAPI, RabbitMQ and Redis

Exploring the architectural setup of how to host GPU intensive PyTorch deep learning models utilizing FastAPI, RabbitMQ and Redis in a scalable way.

Disaster Tweet Classification with RoBERTa and PyTorch

Approaching the Disaster Tweet Classification Kaggle challenge with NLP deep learning.