We are an interdisciplinary team of researchers exploring nature-inspired computing in cybernetics, art, robotics, and games.
Our computer science work investigates how emergent forms of memory and hierarchy allow digital evolution to build programs in dynamic, partially-observable, and multi-task predictive control environments. This work is published in international journals and conference proceedings and has won best paper awards at EuroGP 2017 and GECCO 2017, and a 2018 Silver “Humie” Award for Human-Competitive Results Produced by Genetic and Evolutionary Computation.
Our research-creation works use techniques like genetic programming as raw material for storytelling, activism, and public engagement. The results are mechatronic art/science hybrids that have been exhibited at major international venues such as LABoral Art and Industrial Creation Centre (Gijón, Spain), MUTEK Festival of Digital Creativity (Montreal, Canada), Nuit Blanche (Paris, France), and the Art Gallery of Nova Scotia.
Stephen Kelly is an Assistant Professor in the Department of Computing and Software at McMaster University and a professional media artist. He received his PhD in computer science from Dalhousie University and completed an NSERC post-doctoral fellowship at the BEACON Center for the study of Evolution in Action at Michigan State University. In 2022 he was a visiting researcher at Google Brain. Prior to studying computer science, Stephen completed a Bachelor of Fine Arts at the Nova Scotia College of Art and Design. spkelly@mcmaster.ca
Tanya Djavaherpour is a Master’s student in Computer Science at McMaster University, where she is researching the potential of Tangled Program Graphs (TPG) as a memory mechanism to enhance Deep Reinforcement Learning (DRL) systems. Her research aims to contribute to the development of more robust and efficient AI models capable of learning and adapting in dynamic environments. She holds a Bachelor’s degree in Computer Engineering from Amirkabir University of Technology (Tehran Polytechnic). She is eager to make a positive impact on society through technology.
Ali Naqvi is a second-year MSc student in Computer Science at McMaster University. Ali’s research investigates sequential decision-making models for time series forecasting with a particular interest in developing models that emulate the brain. Previously, Ali completed a B.S in Computer Science at the University of Windsor. Outside of school, he enjoys reading classical literature.
Lihao Bi is a master's student at McMaster University. His research focuses on developing meta-heuristic neural networks and creating hybrid algorithms that combine evolutionary methods with neural networks. At Shanxi University, he worked on improving depth image accuracy and enhancing 3D model textures using advanced image fusion techniques.
He also has extensive industry experience, having worked with Lenovo, Google, and various research institutes. His focus has been on distributed systems, the CUDA framework, and computational acceleration.
Yiding Li is a PhD student and alumnus from McMaster University. He is interested in studying the evolution of emergent behaviours in partially observable dynamic environments.
MEng Report 2024
Pawan Kumar is pursuing his Master's in Computing and Software at McMaster University. His research interests include deep learning and evolutionary computation. He has published work on gesture-controlled systems and using machine learning to recognize different species. Pawan is experienced in various programming languages and frameworks, including TensorFlow and PyTorch, and he aims to develop practical and innovative software solutions.
Lab Alumni
Ecem Heywood is a 3rd year Electrical Engineering Co-op student at McMaster University. She has previous research experience working on environment detection in robotics using reinforcement learning strategies such as Q-learning. Continuing with her passion for robotics and creative learning algorithms, she researched artificial life by designing and developing a program that converts 2D images to 3D organisms using Conway's Game of Life. She also worked on enhancing active learning in embedded systems by designing and developing Braitenberg Vehicles.
Eddie Zhuang is an undergraduate student at McMaster University studying computer science. Eddie's research involved decreasing the computational complexity of evolving Tangled Program Graphs on classic reinforcement learning tasks. His approach focused on estimating fitness values using phylogenetic data. He also worked on streamlining the experimental process by integrating Comet ML, a cloud-based experiment tracking platform.
Sky Quan is an undergraduate student at McMaster University studying computer science. Sky’s research included implementing a Genetic Programming (GP) approach to optimize control tasks in different environments, specifically focusing on evolving solutions for the partially observable pendulum task and mountain car task using Distributed Evolutionary Algorithms in Python (DEAP) and the Gymnasium library. In the future, Sky plans to complete a master’s degree focused on studying different techniques for optimization and problem solving.