Evolutionary computation is a family of algorithms for global optimization inspired by biological evolution
Copyrights and Credit for: brokenmachine86
Genetic Improvement is a subfield of Evolutionary Computation which starts not from randomly created initial individuals, but from functional individuals that are subsequently improved through variation and selection
Picture courtesy: Here
Based at Michigan State University, we work on various projects related to applying evolutionary algorithms in software and the real world. We also study more fundamental questions in Genetic Programming and other EC methods around regulation, open-ended evolution, novelty and search space dynamics. Algorithms influenced by ecology and social systems are another topic of interest, so is the field of Artificial Life in general and its subfield of Artificial Chemistries.
Evolutionary Computation is a field of optimization theory where instead of using classical numerical methods to solve optimization problems, we use inspiration from biological evolution to 'evolve' good solutions.
Artificial intelligence is the attempt to create human-level intelligence processes in computing machines. Specific applications of AI include pattern recognition, e.g. speech and image recognition as well as decision support. Recently artificial neural networks (ANNs) have become very prominent in AI with deep learning processes.
Genetic Improvement is a subfield of Evolutionary Computation which starts not from randomly created initial individuals, but from functional individuals that are subsequently improved through variation and selection.
From the conference website: "EuroGP is the premier annual conference on Genetic Programming (GP), the oldest and the only meeting worldwide devoted specifically to this branch of evolutionary computation. It is always a high-quality, enjoyable, friendly event, attracting participants from all continents, and offering excellent opportunities for networking, informal contact, and exchange of ideas with fellow researchers. It will feature a mixture of oral presentations and poster sessions and invited keynote speakers."
Here are some of our selected research projects
Developing peptides for therapeutic targets or biomarkers is a challenging task within the realm of protein engineering. Evolutionary algorithms are a promising approach for addressing this task. In this context, we have developed POET, a tool based on genetic programming to evolve sequence-function models. These models are then used to predict peptides for experimental evaluation. A POET extension has been introduced using regular expressions. Combining regular expressions with genetic programming provides a promising research direction for the discovery of new efficient peptides.
Mapping between the genotype and phenotype of Tree Genetic Programming is an open field of study, as the genotype may contain sub-structures that contribute nothing to the phenotype. We study this phenomenon and have created a method to remove ineffective nodes from the trees.
The diversity in genetic programming model populations can be exploited to select training samples that maximally inform the development of models through evolution.
A secure and scalable digital leder design to support data centric applications with reliable traceability information sharing across supply chain networks.
Grammatical Evolution aims to evolve programs based on defined grammars given to the tool. A. Murphy works on using GE to improve Large-Language Model performance.
Wolfgang Banzhaf is the John R. Koza Chair for Genetic Programming in the Department of Computer Science and Engineering. His research interests are in the field of bio-inspired computing, notably evolutionary computation and complex adaptive systems.
Email: banzhafw AT msu.edu
My research is focused on developing active learning methods for genetic programming systems to reduce training data requirements for tasks such as symbolic regression, classification, and image segmentation.
Email: hautnath AT msu.edu
I obtained my Ph.D. at NOVA Information Management (NOVA-IMS) School in Lisbon, under the supervision of Professors Leonardo Vanneschi, Mauro Castelli and Raimondo Schettini. My research concerns Evolutionary Computation and its application in the fields of Image Processing and Computer Vision. During my studies, I spent two years working in the Imaging and Vision Laboratory, directed by Prof. Raimondo Schettini, at Università degli Studi di Milano Bicocca (UNIMIB). After getting my Ph.D., I was employed as Auxiliary Invited Professor at NOVA-IMS, where I lectured, supervised students and conducted my research. Now it's time for a new journey at the Banzhaf Lab!
I am currently working on the POET project within the Banzhaf lab, investigating different techniques to improve automatic peptide design. I received my bachelor's degree in theoretical physics from Trinity College Dublin and Ph.D. degree in explainable Artificial Intelligence (AI) (XAI) from the BDS Laboratory, University of Limerick. I was previously a Postdoctoral Research Fellow within the Complex Software Laboratory, University College Dublin, researching software testing and mutation analysis and am currently an assistant professor in UCD. My research interests include grammatical evolution, transfer learning, fuzzy logic, genetic improvement and XAI.
I joined the Banzhaf Lab on January 1st of 2024. I am interested in evolutionary computation, mathematics, and machine learning. I’m working on Linear Genetic programming and Cartesian Genetic programming.
Email: kianinej AT msu.edu
My research focus is on Cartesian Genetic Programming and Linear Genetic Programming, specifically why crossover operators hinder search in CGP but not LGP. I also work on the POET project to develop a general tool for protein screening before synthesis. I enjoy photography, ice cream, hugging my cat, and reading!
Photo Credit: Benjamin Hatto
Email: kocherov AT msu.edu
I am Ruchika Gupta. I am currently interested in image processing and how genetic programming can play a role in current image processing techniques. I am also interested in the subdomain of LLM's and how genetic programming can help play a role in this.
Email: guptaru1 AT msu.edu
After earning my B.S. in Computer Science and Pure Mathematics, I joined the Banzhaf Lab where I am currently a first-year Ph.D. student. My interests include the geometry of Euclidian and non-Euclidian n-space, cellular automata, and alternate models of computation. I aim to integrate these concepts into evolutionary computation to enhance and generalize existing models.
Email: perricoz AT msu.edu
I am a junior undergrad studying Computer Science with a minor in Actuarial Science. My research interests include machine/deep learning and computational finance.
Email: khuctri AT msu.edu
I focus on genetic programming in reinforcement learning tasks. I am particularly interested in how emergent forms of memory and hierarchy allow digital evolution to build programs in partially-observable and multi-task environments. In addition to general problem solving, my collaborative research-creation projects apply bio-inspired computing in art/science hybrids that focus on storytelling, activism, and public engagement.
Email: kellys27 AT msu.edu
Yuan Yuan was a Postdoctoral Fellow with the Department of Computer Science and Engineering and a member of the BEACON Center for the Study of Evolution in Action at Michigan State University, USA. His research interests include evolutionary computation, machine learning, and search-based software engineering.
Email: yyuan AT msu.edu
I finished my Ph.D. at Michigan State University in “Evolution of Decision-Making Systems.” My broad focus is on understanding the cultivation of features that make up intelligent and robust life-like behavior at all levels of complex systems.
Email: jory AT msu.edu
Honglin was a graduate student at the Banzhaf Lab focusing on the intersection of social simulation, artificial life, complex systems, and computational social science. More info about him can be found in his page: carsonhlbao.com
Email: baohongl AT msu.edu
Ken's primary research focus was the overlap of evolutionary algorithms with machine learning. Additionally, he was working on genomic prediction in animals and humans using AI, formulating problems from the video game `Factorio' for research into real-world optimization problems, and in employee scheduling problems.
Email: reidken1 AT msu.edu
My thesis subject was about bioinformatics and was focused on genome annotation using deep learning and genetic programming approaches. I had the opportunity to discover and exploit bio-inspired algorithms that fascinated me. I joined the Banzhaf lab on September 1st of 2022, and I am focusing on the development of a new approach based on evolutionary algorithms for the POET project. I enjoy the fusion of biology with computer science to solve problems.
Email: scalzit1 AT msu.edu
I am CSE PhD student and a researcher at BEACON. I'm interested in bio-inspired algorithms and applying them on complex real life problems. I'm currently working on my thesis Spatial Genetic Programming, Automation in Factorio and POET: Protein Optimization Evolving Tool. I love coding and implementing my ideas specially on computer games!
Email: miralavy AT msu.edu
I am a PhD student in Mechanical Engineering. I am interested in developing a systematic approach to generating constitutive models for engineering materials using Genetic Programming. Using our approach, we can develop a constitutive model with comparable fitness, but it is much simpler and physically reasonable.
Email: guojun2 AT msu.edu
I focus on utilizing digital ledger technologies for developing secure, traceable and trust oriented data sharing applications for food supply chains. My area of research lies in the overlap of blockchains, machine learning and big data technologies. During my time here, I have been focussing on using decentralized ledger technologies to collect and process big data for beef supply chain.
Email: alisalm1 AT msu DOT edu
I am a sophomore undergrad studying Computer Science and Information Science with a Spanish minor. During my time on this team, I have contributed to research on Multi-Task Reinforcement Learning and learned about various elements of evolutionary computation through other team members.
Email: voegerlt AT msu.edu
I am an undergrad student majoring in Computer Science and Mathematics with a minor in Entrepreneurship and Innovation at Michigan State University. I am working on automatic code repair and evolutionary program synthesis. I also love spontaneously traveling, listening to overplayed music and consuming too much coffee.
Email: thammina AT msu.edu
I am an undergraduate student from Johns Hopkins University working as a research assistant in the Banzhaf Lab starting May 2021. I am working on the implementation and evaluation of the genetic programming framework Shackleton that optimizes the sequence of LLVM compiler passes. I was able to add new features to the Shackleton Framework and improve the optimization from 2% to 20%.
Email: sli136 AT jhu.edu
I am a freshman undergrad studying Computer Science with a minor in Computational Mathematics, Science, and Engineering. My research interests include machine learning and evolutionary computation.
Email: wikerale AT msu.edu
MSU – BEACON Center Biomedical and Physical Sciences Building 567 Wilson Road Room 1441 East Lansing, MI 48824