The Effect of Epigenetic Blocking on Multi-Objective Genetic Algorithms

Thursday, July 14, 2022 at 4:00pm to 5:00pm

Building 32-G449, Patil/Kiva, 32-G449 32 Vassar Street

Sizhe Yuen is a final year PhD Student at the University of Southampton. His work focuses on the development of Evolutionary Algorithms using modern biological concepts from the Extended Evolutionary Synthesis. This talk will focus on the concept of epigenetic inheritance. Using a contemporary biological framework based on the Extended Evolutionary Synthesis, epigenetic inheritance is shown as a missing gap despite being a key building block in modern interpretations of how evolution occurs.

Abstract:
Hundreds of Evolutionary Computation approaches have been reported. From an evolutionary perspective they focus on two fundamental mechanisms: cultural inheritance in Swarm Intelligence and genetic inheritance in Evolutionary Algorithms. Contemporary evolutionary biology looks beyond genetic inheritance, proposing a so-called "Extended Evolutionary Synthesis". Many concepts from the Extended Evolutionary Synthesis have been left out of Evolutionary Computation as interest has moved towards specific implementations of the same general mechanisms.

One such concept is epigenetic inheritance. Using a contemporary biological framework based on the Extended Evolutionary Synthesis, epigenetic inheritance is shown as a missing gap despite being a key building block in modern interpretations of how evolution occurs. Epigenetic mechanisms allow quick non- or partially-genetic adaptations to environmental changes. Dynamic multi-objective optimization problems represent similar circumstances to the natural world where fitness can be determined by multiple objectives (traits), and the environment is constantly changing. 

We ask if the advantages that epigenetic inheritance provide in the natural world are replicated in dynamic multi-objective optimization problems. Specifically, an epigenetic blocking mechanism is applied to a state-of-the-art multi-objective genetic algorithm and its performance is compared on three sets of dynamic test functions. The mechanism shows improved performance on 12 of the 16 test problems, providing initial evidence that more algorithms should explore the wealth of epigenetic mechanisms seen in the natural world. These studies are extended to a practical problem, to demonstrate the real-world applicability of such an approach

Event Type

Conferences/Seminars/Lectures

Events By Interest

Academic

Events By Audience

MIT Community, Students, Alumni, Faculty, Staff

Events By School

Schwarzman College of Computing

Group
MIT Quest for Intelligence
Contact Email

provaire@mit.edu

Add to my calendar

Recent Activity