Genetic Algorithms for Optimization & Learning 🤖

Synthetic Intelligence Forum is excited to convene a presentation about applications of genetic algorithms for optimization, adaptation, and learning by Aymeric Vié from the Mathematical Institute in the University of Oxford.

Biography: Aymeric Vié is a DPhil student under the supervision of Doyne Farmer and Rama Cont, at the Centre for Doctoral Training (CDT) on Mathematics of Random Systems of the University of Oxford, and is funded by Fidelity. His research focuses on financial dynamics and risk, at the intersection between computational tools and social sciences.
He is very interested in creating new tools to anticipate, measure and control systemic risk in financial networks, and in developing new paradigms to model the economy from endogenous interactions.
Before starting his PhD in mathematics, Aymeric obtained a Law Bachelor at Paris Sorbonne university, and a political sciences master at Sciences Po. He graduated in the master in Economics from the Paris School of Economics, and was a research fellow at the New England Complex Systems Institute.

Title: Optimization, Adaptation, and Learning with Genetic Algorithms

Abstract: Genetic algorithms, computer programs that simulate natural evolution, are increasingly applied across many disciplines. They have been used to solve various optimization problems from neural network architecture search to strategic games, and to model phenomena of adaptation and learning. Expertise on the qualities and drawbacks of this technique is largely scattered across the literature or former, motivating a compilation of this knowledge at the light of the most recent developments of the field.
In this talk, Aymeric will describe and explain genetic algorithms, their qualities, limitations and challenges, as well as some future development perspectives. Genetic algorithms are capable of exploring large and complex spaces of possible solutions, to quickly locate promising elements, and provide an adequate modelling tool to describe evolutionary systems, from games to economies. They however suffer from high computation costs, difficult parameter configuration, and crucial representation of the solutions.
Recent developments such as GPU, parallel and quantum computing, conception of powerful parameter control methods, and novel approaches in representation strategies, may be keys to overcome those limitations. This talk aims at informing practitioners and newcomers in the field alike about genetic algorithm research, and at outlining promising future directions. It highlights the potential for interdisciplinary collaborations associating genetic algorithms to pulse original discoveries in social sciences, open ended evolution, artificial life and AI.

Profiles of the host and presenter:
• Vik Pant, PhD - https://www.linkedin.com/in/vikpant
• Aymeric Vié, DPhil student - https://www.linkedin.com/in/aymeric-vi%C3%A9-05a480113/

Websites of University of Oxford:
• Mathematical Institute - https://www.maths.ox.ac.uk/
• Mathematics of Random Systems - https://www.ox.ac.uk/admissions/graduate/courses/mathematics-random-systems

Join Synthetic Intelligence Forum online:
• Website - http://www.synthint.ai
• LinkedIn (Page) - https://www.linkedin.com/company/synthint/
• LinkedIn (Group) - https://www.linkedin.com/groups/12092618/
• YouTube - https://www.youtube.com/c/SyntheticIntelligenceForum

Special Thanks to our Partner:
• ET Business Services