Machine-Learning
37 posts
Alloy Composition Optimization: Multi-Objective Materials Design
Using genetic algorithms to optimize alloy compositions for multiple properties simultaneously, balancing strength, hardness, density, and corrosion resistance.
Rocket Motor Optimization: Designing Thrust Profiles
Using genetic algorithms to optimize solid rocket motor grain geometry for target thrust profiles, where physics simulations replace analytical gradients.
HP Lattice Folding: Simplified Protein Structure Prediction
Using genetic algorithms to fold proteins on a lattice model, where the goal is to maximize hydrophobic contacts in a discrete search space.
Lennard-Jones Clusters: Finding Molecular Ground States
Using genetic algorithms to find minimum-energy configurations of atomic clusters, a classic benchmark problem in computational physics.
Island Models: What Splitting the Population Actually Buys
Islands, migration and topology, measured at a matched budget. The results point the opposite way to the usual advice.
Genetic Algorithms: Evolution as Optimization
An introduction to genetic algorithms: how evolutionary principles solve optimization problems, from selection and crossover to mutation and fitness landscapes.
category_encoders in the Wild: A Tour of the Research
A look at the surprisingly diverse research that has cited the category_encoders library, from cleaning up polluted water to catching financial criminals.
Training a Deep Q-Network for Trading
How we're using Deep Q-Networks to learn trading decisions, and the techniques that make training stable enough to actually work.
Joining Scale Venture Partners as Chief Data Scientist
Joining Scale Venture Partners as Chief Data Scientist to build AI infrastructure augmenting investment decisions in venture capital.
Perplexity 101: How Language Models Measure Surprise
A deep dive into perplexity: the metric that tells us how 'surprised' a language model is by text and why it matters for AI detection.