A researcher specializing in biologically-inspired artificial intelligence and robust neural network architectures. My work bridges neuroscience principles with machine learning, focusing on developing systems that exhibit the stability and resilience characteristic of biological intelligence. I approach research with commitment to both theoretical rigor and practical impact, developing methods that are grounded in biological principles while addressing fundamental limitations in current artificial neural networks.

Research Interests

My research program centers on creating artificial intelligence systems that embody principles of biological robustness and adaptability:

Biologically-Inspired Neural Architectures

Developing neural network layers and systems that incorporate homeostatic regulation, self-repair mechanisms, and multi-scale temporal dynamics inspired by biological nervous systems.

Robust and Resilient AI Systems

Addressing the brittleness of artificial neural networks through bio-inspired stability mechanisms that enable consistent performance under perturbations, distribution shifts, and adverse conditions.

Multi-Scale Temporal Coordination

Investigating how coordination across multiple temporal scales—from milliseconds to hours—can enhance the efficiency, stability, and recovery capabilities of artificial neural systems.

Neuromorphic and Brain-Inspired Computing

Translating principles from neuroscience and evolutionary biology into computational frameworks that advance the capabilities of artificial intelligence.

General AI Agent Systems

Building integrated platforms combining LLMs, computer vision, and researching multi-agent collaboration, developing cross-domain knowledge transfer, and creating benchmarks for general AI capabilities.