Zimeng Lyu

Zimeng Lyu

Ph.D. Candidate

Ph.D. Candidate in Computer Science specializing in advanced ML, neural architecture search, and real-time adaptation. Delivered $7.3M in power plant cost savings and beat market benchmarks with evolved RNN strategies. Proficient in C++, Python, PyTorch, Docker, Spark, and distributed computing for large-scale AI solutions. Additionally, I serve as an instructor for a master’s-level Software Engineering for Data Science core course, designing four real-world, large-scale data pipeline applications.

Thesis Advisor: Dr. Travis Desell.

Research Areas

Time Series Forecasting

Online and Offline Time Series Forecasting, Stock Return Predictions

Neural Architecture Search

NeuroEvolution, Recurrent Neural Networks

Minimally Supervised Learning

Self Organizing Maps, Topological Projections

Latest News

January 2025

EvoAPPs Paper Acceptance

April 2024

WCCI IJCNN acceptance

June 2023

Applied Soft Computing Journal Paper Accepted

Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting

Read Paper