Based on recent advances in machine learning more and more complex artificial neural networks are developed that become increasingly proficient in mimicking perceptual inference abilities of humans and animals. As a side effect of their popularity in technology, the increasing availability and diversity of high-performing neural network models opens a new door for studying the neural mechanisms of robust decision making.
Important differences between these networks are the presence or absence of feedback connections, the presence or absence of stochasticity, and the diversity of different nonlinear mechanisms. The existence of this diversity mirrors important discussions in neuroscience on the role and effect of feedback signals is in the brain [1], whether the brain represents and computes with probabilities [2], whether feedback signals are essential for performing probabilistic inference in hierarchical models [3], and whether neural stochasticity can be interpreted in terms of sampling [4] or regularization such as dropout [5].
As a joint effort between theoreticians and experimentalists, the goal of this Sparks workshop will be to survey and discuss the role of these mechanisms for robust decision making in artificial and real neural networks and to derive discriminative experimental tests and tools that seem most promising to analyze them.
[1] Gilbert & Li, Nat Rev Neuro 2013
[2] Pouget et al, Nat Rev Neuro 2013
[3] Lee & Mumford, JOSA 2003
[4] Fiser et al., TICS 2010
[5] Srivastava et al, JMLR 2014
Confirmed Speakers:
|
|
|
Organizers: |
|
|
Poster/ Contributed Talks: Poster submissions are highly encouraged. We also may have a small number of slots for contributed talks. Deadline for abstract submission is May, 31th.
Registration/Fees: Attendance is limited to 70 participants. Seats will be allocated on first-come-first-served basis. Please register on the registration website until May, 31th.
Workshop registration only (incl. lunch, dinner and coffee breaks):
- For members of the Bernstein Network and the Bernstein Association for Computational Neuroscience: 40 Euro
- For non-members: 100 Euro
If you want to become a Bernstein member, please click here.
The registration is valid after receipt of money. After register you receive the bank account details per email.
Location:
Max-Planck-House
Spemannstr. 36
72076 Tübingen
Accommodation: A few rooms are reserved for workshop participants (10-12th). If you are interested, please contact Stefanie Wanner.
A list of hotels can be found here.
Schedule:
Thursday (June 11th) | |
9:00 - 09:30 | Matthias Bethge (intro: Understanding biological and artificial neural networks) |
Friday (June 12th) | |
09:00 - 09:30 | Ralf Haefner (intro: decision making) |
Expected outcomes of this workshop will consist of:
- Cross-inspiration between theoretical insights on robust decision making in artificial neural networks and systems neuroscience.
- New specific ideas on the use of stochasticity and feedback in artificial neural networks.
- New neurophysiological and psychophysical predictions based on potential algorithms that the brain might employ for robust decision making.
- Highlight analysis techniques for high - dimensional data that make full use of modern population recordings and genetic tools.
Contact: Stefanie Wanner