Living Memory Dynamics - A novel framework for narrative-generating episodic memory with creative leaps. Features the Joshua R. Thomas Memory Equation.

A neuromorphic computing approach to endpoint detection using Spiking Neural Networks (SNN) and Kolmogorov-Arnold Networks (KAN) for real-time system call anomaly detection with symbolic regression compression.

Bio-inspired adapters that improve foundation models beyond LoRA fine-tuning. 50+ neuroscience mechanisms searched via Thompson sampling over 10²² configurations. Validated on 20 benchmarks (85% win rate). Includes AI bias detection across major models.

Bio-inspired continual learning library in PyTorch. Features dynamic neurogenesis, synaptic consolidation, and fast/slow weights to prevent catastrophic forgetting. Learn animals + vehicles + adapt to noise—all without destroying previous knowledge.

Personal portfolio - AI systems, simulations, generative experiments & open-source tools