Stephen

UCR_Time_Series_Classification_Deep_Learning_Baseline. Fully Convlutional Neural Networks for state-of-the-art time series classification

Imaging-time-series-to-improve-classification-and-imputation. Python 3.6+ (only)

kaggle_diabetic_RAM. Extended Retinopathy Detection Challenge with the Regression Activation Map for visual explaination

Deconv_SAX. Representation Learning with Deconvolutional Networks for Multivariate Time Series

Encoding_Temporal_Markov_Dynamics_in_Graph_for_Visualizing_and_Mining_Time_Series. Python

agent-harness-engineering. 91 production-proven patterns for building AI agents, extracted from a 512K-line codebase. Covers agentic loops, tool systems, permissions, MCP, prompt caching, multi-agent orchestration.

ANRAT. Adaptive Normalized Risk-Averting Training For Deep Neural Networks

causal-edge. The first agent-native quant framework. AGENTS.md is the architecture. Structural tests are the guardrails. Abel Proof is the validation engine.