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

AI-driven brain tumor detection using Transfer Learning (ResNet50, DenseNet121) and Metaheuristic Optimization (Grey Wolf Optimizer). Features bio-inspired feature selection and comparative visual analytics for medical MRI classification.

Bio-inspired distributed neuromorphic control stack for physical AI.

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.

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.

Started this project back in 2018 with a small group of fellow students in high school. We progressively improved the program and ran through multiple iterations of it as we understood better how to incorporate biological brain dynamics into code using Python. The following program is the last complete version we developed in 2022.

Bio-inspired neural architectures research: differentiable local plasticity, sparse coding, and few-shot learning. Empirical study toward post-LLM cognitive architectures (Omniglot benchmark). Workshop paper in preparation.

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.

Babyoid (DOA) investigates how intelligence can emerge through development, adaptation, memory formation, and evolution. Inspired by Artificial Life, the framework introduces computational seeds and Digital DNA to study the growth of artificial organisms rather than predefined intelligent architectures.

Biologically-inspired agent swarm: AI cells spawn, specialize, and trade energy to grow an organism around a task.

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

Computational bioacoustic topology framework for modeling birdsong as a latent dynamical system using manifold embeddings, motif grammars, toroidal geometry, and orbital flow dynamics.