I'm a biomedical ML and robotics researcher at Washington University in St. Louis, focusing on the intersection of computational neuroscience and machine learning. My work explores how biological neural circuits—particularly from Drosophila connectomes—can inspire more efficient and adaptable artificial learning systems.

Current Research Focus:

• 🦟 Leveraging Drosophila whole-brain connectomes for bio-inspired neural architectures
• 🔄 Developing plasticity-guided learning algorithms with dopamine-modulated mechanisms
• 🤖 Deploying edge AI for closed-loop behavioral control systems
• 📊 Building computational tools for neuroscience data analysis

A bio-inspired recurrent neural network that combines Drosophila connectome constraints with valence-modulated plasticity. This novel approach uses reservoir computing with realistic circuit structures for innate odor processing pathways, enhanced by learnable dopamine-gated mechanisms.

Key Features:

• 🧬 Biologically constrained network topology from real connectome data
• 🎯 Dopamine-modulated synaptic plasticity for reward-based learning
• ⚡ Efficient reservoir computing architecture
• 🔬 Applications in understanding insect olfactory learning

Python tools for working with the Database of Odorant Responses (DoOR), enabling researchers to access and analyze comprehensive odor response data across multiple species.

Automated behavioral analysis system for quantifying and scoring Drosophila behaviors in closed-loop experimental setups.

Machine Learning & AI

Python PyTorch TensorFlow NumPy Scikit--learn

Neuroscience & Data Analysis

Jupyter Pandas MATLAB

Robotics & Embedded Systems

ROS Arduino Raspberry Pi

Tools & Platforms

Git Linux Docker

• Bio-Inspired Neural Networks: Translating biological learning mechanisms into artificial systems
• Connectomics: Analyzing and utilizing whole-brain connectivity data from model organisms
• Neuromodulation: Understanding how dopamine and other modulators shape learning and plasticity
• Reservoir Computing: Leveraging recurrent dynamics for efficient temporal processing
• Closed-Loop Systems: Real-time behavioral feedback and adaptive control
• Edge AI: Deploying efficient ML models on resource-constrained hardware

I'm always interested in collaborating on projects at the intersection of neuroscience, machine learning, and robotics. Whether you're working on:

• 🧬 Connectome-inspired neural network architectures
• 🤖 Bio-inspired robotics and control systems
• 📊 Computational neuroscience tools and databases
• 🎓 Educational initiatives in neuroAI

Feel free to reach out! You can find me on LinkedIn or explore my research projects here on GitHub.