PhD - Bayesian methods for Spiking Networks F/M

Description

We seek a PhD student to work on Bayesian training techniques for spiking neural networks.  Funded by the Swiss NSF, the project is a collaboration between Idiap Research Institute in Switzerland and the Department of Mathematics at Mahidol University in Bangkok, Thailand.

Spiking neurons can be thought of as a type of recurrent neuron that communicates using short bursts of energy.  Such neurons are much closer to current understanding of biological mechanisms than those used in current deep learning solutions.  In addition to promising better understanding of biological processes, spiking nets have persuasive low-power implications.  However, they present difficulties associated with their binary nature and non-differentiability of the emitted spikes.

At Idiap, the project will build on our recent work that has shown that spiking networks are plausible solutions for speech processing tasks.  The Bayesian approach will be twofold: In a first thread we will attempt to show that prior information can compensate for discontinuities in the error landscape arising from the binary nature.  In a second thread, we will use Bayesian Optimisation techniques to handle the increased number of hyperparameters associated with spiking neurons.

All work will happen in close collaboration with our partners in Thailand.  The successful candidate will spend around one year of their study seconded to Mahidol, with a counterpart at Mahidol also spending one year at Idiap.

Sought profile

The ideal Ph.D student should have a master (or equivalent) degree in engineering, computer science, physics or mathematics.
They should have a good background in mathematics, statistics, and programming (C/C++, Python, scripting languages).
The SNSF SPIRIT program is especially concerned with gender and identity inclusivity; we will emphasise this through the hiring process.  In this sense, we particularly encourage applications from female candidates.

The student will be registered at EPFL and located at Idiap.
The position is available from early 2025, fully funded for four years.

About Idiap

Idiap is a research institute of national importance that engages in fundamental research, education and technology transfer in artificial intelligence, machine learning and signal processing. Idiap offers competitive salaries and conditions in a young, high-quality, dynamic, and multicultural environment. Idiap is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. English is the official working language.

At Idiap we place great emphasis on diversity and we know diversity fosters creativity and innovation. We are committed to equality of opportunity, to being fair and inclusive, and to being a place where we all belong. Employment at Idiap is based solely on a person's merit and qualifications. Idiap does not discriminate against any employee or applicant because of race, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, marital status, pregnancy, or any other basis protected by law.

For frequently asked questions (FAQs) about living in Switzerland, please go to https://www.idiap.ch/en/faq

Required languages

• English - Level advanced

Réf: 57e95415-2b58-43e5-aacb-80e6e88fe2b7