<aside> <img src="/icons/home_gray.svg" alt="/icons/home_gray.svg" width="40px" />

Home

</aside>

<aside> <img src="/icons/school_gray.svg" alt="/icons/school_gray.svg" width="40px" />

Research

</aside>

<aside> <img src="/icons/book-closed_gray.svg" alt="/icons/book-closed_gray.svg" width="40px" />

Blog

</aside>

<aside> <img src="/icons/book-closed_gray.svg" alt="/icons/book-closed_gray.svg" width="40px" />

Simultaneous detection and mapping in the olfactory bulb

ongoing project

Keywords: odor inference, recurrent neural networks, mirrored Langevin dynamics

A blog for Computational Models for Fast Inference in the Mammalian Olfactory System

</aside>

<aside> <img src="/icons/book-closed_gray.svg" alt="/icons/book-closed_gray.svg" width="40px" />

Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration

Keywords: explore-exploit, stochastic Hopfield network, Thompson sampling, decision under uncertainty, brain-inspired algorithm, reinforcement learning

TL;DR: We demonstrate that a brain-inspired stochastic Hopfield network can achieve efficient, human-like, uncertainty-aware exploration in bandit and MDP tasks.

ICLR 2025 (see public review); Poster presentation at **MAIN 2024 and NAISys [**Poster]

</aside>