Ilya Orson 's Projects
Temporal fork of https://pypi.org/project/alamopy/ adapted for a demo in a lecture.
đ§âđĢ 60 Implementations/tutorials of deep learning papers with side-by-side notes đ; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), đŽ reinforcement learning (ppo, dqn), capsnet, distillation, ... đ§
Applications of Simulation and Automation
Attention based model for learning to solve different routing problems
A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges
Papers about explainability of GNNs
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
A curated list of resources dedicated to reinforcement learning applied to cyber security.
Neural ODEs as Feedback Policies for Nonlinear Optimal Control (IFAC 2023) https://doi.org/10.1016/j.ifacol.2023.10.1248
Cyber Operations Research Gym
Code for the book "The Elements of Differentiable Programming".
A documentation generator for Julia.
Material for the hands-on tutorial on Graph Deep Learning held at the Alan Turing Institute
Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks.
Public-facing repo for organising activities+ archiving material relating to the Graph Neural Network reading group.
Representing robots as graphs for reinforcement-learning in PyBullet locomotion environments.
GNN-RL Compression: Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
Workshop for GNN at RIIAA
A curated list of graph-based fraud, anomaly, and outlier detection papers & resources
A gymnasium environment for the job shop problem using the disjunctive graph approach
Official LaTeX templates employing the Imperial College London brand.
đšī¸ A diverse suite of scalable reinforcement learning environments in JAX
A 6 Lesson course teaching everything you need to know about harnessing GitHub Copilot and an AI Paired Programing resource.
MLX implementation of GCN, with benchmark on MPS, CUDA and CPU (M1 Pro, M2 Ultra, M3 Max).