<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
Dear Moderator of the vision list, <br>
<br>
Could you please post that announce below?<br>
<br>
Best,<br>
Robin
<div class="moz-forward-container"><br>
<br>
<br>
<br>
<b>Beating Roger Federer: </b><b><br>
</b><b>Modeling visual learning and expertise through a
bioinspired neural network embedded in an electronic device</b><br>
<br>
<b>Goal: </b>PhD grant. <br>
<br>
<b>When: </b>starting from September 2018 (date may be flexible
to some extent)<br>
<br>
<b>Topic: </b>How do expert tennis players, like Roger Federer
for example, predict if a ball will bounce in or out the field to
decide if it should be played or not? After thousands of
trajectory presentations, best champions have developed
extraordinary skills in such a task, but little is known on how
the visual system turns selective to spatiotemporal properties of
the visual stimulus (e.g., 3D position, velocity and acceleration)
and learns how to make an efficient use of it.<br>
The goal of the project is to build an embedded system – based on
FPGA circuits and ARM processor – an artificial neural network
which would replicate – and perhaps beat – the visual and
anticipatory performances of these expert players. <br>
To achieve this goal successfully, we will develop a bio-inspired
neural network, based on some of the key properties of human
vision: the Smart NeuroCam (GST company) will be used to reproduce
the retina functioning. It triggers its message under the form of
spikes, in an asynchronous way (without any concept of frame per
second), responding to spatial or temporal changes in the pattern
of illumination. Several kinds of pre-processing filters can be
implemented in VHDL language directly in the FPGA circuits, and
the output is then sent to a neural network. The artificial
network will learn to use this message, applying a simple learning
rule, the Spike-Timing-Dependent Plasticity (STDP). This rule
allows each neuron to become selective to a particular property of
the stimulus, completely autonomously and with no supervision.
Several layers will be built to allow perceiving more and more
complex properties of the visual scene. Once the network will be
established, its performances will be assessed in different
conditions of learning and compared to those of the best tennis
players.<br>
<br>
The project is funded by a French National Research Agency (ANR),
involving two sites and several researchers: <br>
Robin Baurès, Benoit Cottereau, Timothée Masquelier and Simon
Thorpe, CerCo, Toulouse.<br>
Michel Paindavoine, GST, Dijon.<br>
<br>
<b>Where: </b>The candidate will be based at CerCo, Toulouse
(France), and will make the interface with the two sites, with
regular trips. The computational neuroscience part will be done at
Toulouse, and electronic part at Dijon. <br>
<br>
<b>Tasks:</b><br>
Matlab (or Python) based simulations of numerical filters. These
filters will be applied to the image processing from which spikes
are generated and then sent to feed the neural network and STDP
learning mechanism.<br>
VHDL coding to implement these numerical filters into the FPGA
circuits of the cameras<br>
C/C++ coding of the neural network and STDP mechanism that should
work on an embedded ARM processor system<br>
Experimental tests that will allow evaluating the performance of
the whole system, from spikes generation to visual properties
learning of the embedded system, to predict tennis ball’s
trajectories <br>
<br>
<b>Required skills: </b><br>
Strong knowledge on electronic, and openness to computational
neurosciences<br>
Knowledge in signal-image processing, and artificial neural
network<br>
Interest for multidisciplinary research<br>
Ability to turn smoothly autonomous, once the road has been set<br>
Ability to be at the interface of two scientific fields and two
working areas<br>
Programming with Matlab and/or Python for simulating the neural
network<br>
Programming in VHDL language for FPGA circuits<br>
Programming in C/C++ language for porting the algorithms on ARM
microprocessors<br>
French is not a requirement if fluent in English, but willingness
to learn would be beneficial <br>
<br>
<b>C</b><b>itizenship Eligibility: </b>For security / defense
reasons, an evaluation will be made of the candidates before any
possible acceptation. <br>
<br>
<b>Relevant publications for the project:</b><br>
Masquelier, T., Guyonneau, R. & Thorpe S.J. (2009).
Competitive STDP-Based Spike Pattern Learning. Neural Comput,
21(5),1259-1276.<br>
Masquelier, T. & Thorpe, S.J. (2007). Unsupervised learning of
visual features through spike timing dependent plasticity. PLoS
Comput Biol, 3(2):e31.<br>
Cottereau, B.R., McKee, S.P. & Norcia, A.M. (2014). Dynamics
and cortical distribution of neural responses to 2D and 3D motion
in human. Journal of Neurophysiology 111(3), 533-543.<br>
SmartNeuroCam de GST : <a class="moz-txt-link-freetext"
href="https://gsensing.eu/fr/category/sections/products"
moz-do-not-send="true">https://gsensing.eu/fr/category/sections/products</a><br>
<br>
<b>Contact:</b><br>
Robin Baurès, PhD<br>
Associate Professor<br>
CerCo, Université Toulouse 3, CNRS<br>
CHU Purpan, Pavillon Baudot<br>
31059 Toulouse Cedex 9 – France<br>
Office phone: 0033 (0)5 62 74 62 15<br>
Email : <a class="moz-txt-link-abbreviated"
href="mailto:robin.baures@cnrs.fr" moz-do-not-send="true">robin.baures@cnrs.fr</a><br>
<br>
Pr Michel Paindavoine<br>
GlobalSensing Technologies<br>
14, rue Pierre de Coubertin<br>
21000 Dijon<br>
email : <a class="moz-txt-link-abbreviated"
href="mailto:michel.paindavoine@gsensing.eu"
moz-do-not-send="true">michel.paindavoine@gsensing.eu</a>
<pre class="moz-signature" cols="72">--
**************************************************
Robin Baurès, PhD
Maitre de Conférences | Associate Professor
CerCo, Université Toulouse 3, CNRS
CHU Purpan, Pavillon Baudot
31059 Toulouse Cedex 9 - France
Office phone: 0033 (0)5 62 74 62 15
Mail: <a class="moz-txt-link-abbreviated" href="mailto:robin.baures@univ-tlse3.fr" moz-do-not-send="true">robin.baures@univ-tlse3.fr</a> | <a class="moz-txt-link-abbreviated" href="mailto:robin.baures@cnrs.fr" moz-do-not-send="true">robin.baures@cnrs.fr</a>
**************************************************</pre>
</div>
</body>
</html>