Travis Desell
Scholar

Travis Desell

Google Scholar ID: K9xdZDkAAAAJ
Associate Professor, Rochester Institute of Technology
NeuroevolutionEvolutionary AlgorithmsData ScienceScientific ComputingHigh Performance Computing
Citations & Impact
All-time
Citations
1,203
 
H-index
18
 
i10-index
36
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Research Experience
  • - Developed the EXACT (Evolutionary eXploration of Augmenting Convolutional Topologies) and EXAMM (Evolutionary eXploration of Augmenting Memory Models, formerly known as EXALT) algorithms.
  • - Principal Investigator for the National General Aviation Flight Information Database (NGAFID), a project aimed at monitoring and predicting potential flight safety issues.
  • - Co-PI on NSF Award #2225354 CPS: Small: Informed Contextual Bandits to Support Decision-Making for Intelligent CPS, which focuses on time series forecasting, anomaly detection, and error correction using neuroevolution.
  • - A main contributor to the development of both the compiler and runtime for SALSA and SALSA Lite, programming languages based on the actor model of computation, designed for easy development of concurrent and transparently distributed applications.
Background
  • A professor specializing in Data Science, focusing on applying machine learning to large-scale, real-world datasets. His interests lie at the intersection of evolutionary algorithms and neural networks, or 'neuro-evolution', and developing systems for practical scientific use with high performance and distributed computing.
Miscellany
  • Currently recruiting a new PhD student with a strong background in software engineering and expertise/interest in natural language processing, large language models, web development, and web scraping.