Generative Modeling
Variational Autoencoder architecture diagram showing encoder, latent space, and decoder

Modern PyTorch Techniques for VAEs: A Hands-On Tutorial

A comprehensive guide to implementing Variational Autoencoders (VAEs) in PyTorch. Covers the ELBO objective, …

Scientific Computing
Comparison of IQCRNN (Our Method) vs standard Policy Gradient showing training curves, phase portraits, and state trajectories for control tasks

Certified Robustness: Projecting Neural Networks onto Stability Constraints

A PyTorch re-implementation of IQCRNN, enforcing strict stability guarantees on Recurrent Neural Networks via Integral …...

Natural Language Processing
Heatmap visualization of the EigenNoise analytical co-occurrence prior matrix showing word rank relationships

EigenNoise: Data-Free Word Vector Initialization

Investigation into EigenNoise, a data-free initialization scheme for word vectors that approaches pre-trained model …...

Machine Learning Fundamentals
Vintage slot machine with multiple arms representing the multi-arm bandit problem in machine learning

A Framework for Multi-Arm Bandit Problems

Framework for understanding multi-arm bandit algorithms through five dimensions. Covers exploration vs exploitation and …

Machine Learning Fundamentals
Various symmetric and repetitive patterns generated by Compositional Pattern Producing Networks

HyperNEAT: Scaling Neuroevolution with Geometric Patterns

How HyperNEAT uses indirect encoding and geometric patterns to evolve large-scale neural networks with biological …

Machine Learning Fundamentals
NEAT genome encoding diagram showing node genes and connection genes with innovation numbers

NEAT: Evolving Neural Network Topologies

Learn about NEAT's approach to evolving neural networks: automatic topology design, historical markings, and speciation …

Scientific Computing
Cartesian Genetic Programming graph showing input nodes, function nodes, and output nodes with active and inactive connections

Cartesian Genetic Programming in Julia

An implementation of Cartesian Genetic Programming (CGP) featuring NEAT-like speciation mechanics and novel crossover …...

Generative Modeling
Wasserstein distance visualization showing Earth-Mover distance concept for GAN training

GAN Objective Functions: A Comprehensive Guide

Complete guide to GAN objective functions including WGAN, LSGAN, Fisher GAN, and more. Understand which loss function to …

Generative Modeling
Illustration of GAN training process showing adversarial competition between generator and discriminator

Understanding Generative Adversarial Networks (GANs)

Learn about GANs with intuitive explanations and mathematical foundations. Learn how adversarial networks generate …

Scientific Computing
Radix-2 DIT butterfly diagram showing the fundamental FFT operation with twiddle factor multiplication

FFTW Compiler in Haskell

Reverse-engineering the genfft logic to generate optimized C kernels for Fast Fourier Transforms using Haskell …...

Scientific Computing
Flowchart diagram showing the recursive backtracking algorithm for constraint satisfaction in schedule generation

Term Schedule Optimizer

A constraint satisfaction solver built to generate conflict-free university schedules from web-scraped course data....