Science & Tech
Research, software, and side projects.
Personal projects
This Website
A personal website built with Astro — part portfolio, part photo album, part project log.
Mountaineering Preparation Assistant
A conversational AI assistant for technical mountaineering preparation — route research, conditions, weather, and avalanche forecasts, grounded in real data sources.
Research
Hyperparameters and Representational Geometry in Neural Networks
Do the training choices you make when building a neural network affect what it learns to represent internally? Yes, substantially, even among networks that perform comparably on the same task. This has direct implications for research that uses neural networks as models of the brain.
Hierarchical Reinforcement Learning as Creative Problem Solving
A theoretical and experimental project exploring the relationship between hierarchical reinforcement learning, the psychology of insight, and computational creativity.
Modeling Cognitive Control: RNNs and Representational Similarity Analysis
A published computational neuroscience study using RSA to compare how recurrent neural networks and the human anterior cingulate cortex represent hierarchically structured task sequences. Networks with explicit goal units better account for the representational geometry of human ACC.
Atari ACC Model
A computational model of the anterior cingulate cortex, developed during a postdoc in Clay Holroyd's lab at Ghent University. ACC modules trained on top of a deep RL agent playing Q-bert learn to track and represent the agent's internal state — demonstrating that a separate observer module can recover structured, abstract representations of a complex neural system in action.
CV
Publications, professional background, and downloadable PDF.