Connectionists: Two PhD positions

[Phil Garner]

Dear Colleagues,

The Idiap Research Institute in partnership with the Department of 
Mathematics at Mahidol University seek two PhD students to work on 
Bayesian Optimisation and training techniques for spiking neural 
networks.  Funded by the Swiss NSF, one student will be based in 
Martigny in the Swiss alps, the other in Bangkok in Thailand.  Exchanges 
between the two are planned.

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 many hyperparameters, 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.

At Mahidol, the team will be responsible for designing frameworks for 
LPNet and neural networks to address the vehicle routing problem (VRP). 
The project will explore the effectiveness of these approaches in 
solving VRP and identify their limitations. The ultimate aim is to 
enhance VRP solutions through our spiking neural network (SNN) framework.

The ideal student should have a master's (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). Candidates should have a deep 
understanding of ANNs and, ideally, familiarity with SNNs.

For more information and to apply,
for Idiap: 
https://careers.werecruit.io/en/idiap/offers/phd---bayesian-methods-for-spiking-networks-57e954
for Mahidol: 
https://mathematics.sc.mahidol.ac.th/scholarship-for-phd-in-mathematics-swiss-nsf-en/

The SNSF SPIRIT program is especially concerned with gender and identity 
inclusivity; we will emphasize this through the hiring process.  In this 
sense, we particularly encourage applications from female candidates.

Sincerely,
-- 
Phil Garner
http://www.idiap.ch/~pgarner