Publications

2024

Journal Articles

High-performance deep spiking neural networks with 0.3 spikes per neuron

A. Stanojevic; S. A. Wozniak; G. Bellec; G. Cherubini; A. Pantazi et al. 

Nature Communications. 2024. Vol. 15, num. 1. DOI : 10.1038/s41467-024-51110-5.

Fast learning without synaptic plasticity in spiking neural networks

A. Subramoney; G. Bellec; F. Scherr; R. Legenstein; W. Maass 

Scientific Reports. 2024. Vol. 14, num. 1, p. 8557. DOI : 10.1038/s41598-024-55769-0.

Computational models of intrinsic motivation for curiosity and creativity

S. Becker; A. Modirshanechi; W. Gerstner 

Behavioral and Brain Sciences. 2024. Vol. 47. DOI : 10.1017/S0140525X23003424.

Theses

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

A. Modirshanechi / W. Gerstner (Dir.)  

Lausanne, EPFL, 2024. 

Conference Proceedings

Expand-and-Cluster: Parameter Recovery of Neural Networks

2024. 41st International Conference on Machine Learning (ICML 2024).

2023

Journal Articles

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

C. F. Park; M. Barzegar-Keshteli; K. Korchagina; A. Delrocq; V. Susoy et al. 

Nature Methods. 2023. Vol. 21, num. 1. DOI : 10.1038/s41592-023-02096-3.

An exact mapping from ReLU networks to spiking neural networks’ [Neural Networks(vol168, pg 74, 2023)

A. Stanojevic; S. Wozniak; G. Bellec; G. Cherubini; A. Pantazi et al. 

Neural Networks. 2023. Vol. 169, p. 622 – 622. DOI : 10.1016/j.neunet.2023.10.057.

Surprise and novelty in the brain

A. Modirshanechi; S. Becker; J. Brea; W. Gerstner 

Current Opinion In Neurobiology. 2023. Vol. 82, p. 102758. DOI : 10.1016/j.conb.2023.102758.

Computational models of episodic-like memory in food-caching birds

J. Brea; N. S. Clayton; W. Gerstner 

Nature Communications. 2023. Vol. 14, num. 1. DOI : 10.1038/s41467-023-38570-x.

An exact mapping from ReLU networks to spiking neural networks

A. Stanojevic; S. Woźniak; G. Bellec; G. Cherubini; A. Pantazi et al. 

Neural Networks. 2023. Vol. 168, p. 74 – 88. DOI : 10.1016/j.neunet.2023.09.011.

Theses

Supervised learning and inference of spiking neural networks with temporal coding

A. Stanojevic / W. Gerstner; S. A. Wozniak (Dir.)  

Lausanne, EPFL, 2023. 

A theory of memory consolidation and synaptic pruning in cortical circuits

G. Iatropoulos / H. Markram; W. Gerstner (Dir.)  

Lausanne, EPFL, 2023. 

2022

Journal Articles

Modulation of working memory duration by synaptic and astrocytic mechanisms

S. Becker; A. Nold; T. Tchumatchenko 

Plos Computational Biology. 2022. Vol. 18, num. 10, p. e1010543. DOI : 10.1371/journal.pcbi.1010543.

A taxonomy of surprise definitions

A. Modirshanechi; J. Brea; W. Gerstner 

Journal of Mathematical Psychology. 2022. Vol. 110, p. 102712. DOI : 10.1016/j.jmp.2022.102712.

Brain signals of a Surprise-Actor-Critic model: Evidence for multiple learning modules in human decision making

V. Liakoni; M. P. Lehmann; A. Modirshanechi; J. Brea; A. Lutti et al. 

Neuroimage. 2022. Vol. 246, p. 118780. DOI : 10.1016/j.neuroimage.2021.118780.

2021

Journal Articles

Spike frequency adaptation supports network computations on temporally dispersed information

D. Salaj; A. Subramoney; C. Kraisnikovi; G. Bellec; R. Legenstein et al. 

Elife. 2021. Vol. 10, p. e65459. DOI : 10.7554/eLife.65459.

Learning in Volatile Environments With the Bayes Factor Surprise

V. Liakoni; A. Modirshanechi; W. Gerstner; J. Brea 

Neural Computation. 2021. Vol. 33, num. 2, p. 269 – 340. DOI : 10.1162/neco_a_01352.

Testing two competing hypotheses for Eurasian jays’ caching for the future

P. Amodio; J. Brea; B. G. Farrar; L. Ostojic; N. S. Clayton 

Scientific Reports. 2021. Vol. 11, num. 1, p. 835. DOI : 10.1038/s41598-020-80515-7.

Conference Papers

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

B. Şimşek; F. Ged; A. Jacot; F. Spadaro; C. Hongler et al. 

2021. 38 th International Conference on Machine Learning (ICML 2021), Virtual, July 18-24, 2021. p. 9722 – 9732.

Posters

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

B. A. Illing; J. Ventura; G. Bellec; W. Gerstner 

35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 6-14, 2021.

Fitting summary statistics of neural data with a differentiable spiking network simulator

G. Bellec; S. Wang; A. Modirshanechi; J. M. Brea; W. Gerstner 

35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 6-14, 2021.

Student Projects

CauseOccam: Learning Interpretable Abstract Representations in Reinforcement Learning Environments via Model Sparsity

S. Volodin 

2021.

2020

Journal Articles

On the choice of metric in gradient-based theories of brain function

S. C. Surace; J-P. Pfister; W. Gerstner; J. Brea 

Plos Computational Biology. 2020. Vol. 16, num. 4, p. e1007640. DOI : 10.1371/journal.pcbi.1007640.

Conference Papers

Spiking Neural Networks Trained With Backpropagation For Low Power Neuromorphic Implementation Of Voice Activity Detection

F. Martinelli; G. Dellaferrera; P. Mainar; M. Cernak 

2020. IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, SPAIN, May 04-08, 2020. p. 8544 – 8548. DOI : 10.1109/ICASSP40776.2020.9053412.

A Bin Encoding Training Of A Spiking Neural Network Based Voice Activity Detection

G. Dellaferrera; F. Martinelli; M. Cernak 

2020. IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, SPAIN, May 04-08, 2020. p. 3207 – 3211. DOI : 10.1109/ICASSP40776.2020.9054761.

2018

Conference Papers

Decoupling Backpropagation using Constrained Optimization Methods

A. Gotmare; V. Thomas; J. M. Brea; M. Jaggi 

2018. ICML 2018 35th International Conference on Machine Learning, Stockholm, SWEDEN, July 10-15, 2018.

Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation

D. S. Corneil; W. Gerstner; J. M. Brea 

2018. ICML 2018 35th International Conference on Machine Learning, Stockholm, SWEDEN, July 10-15, 2018.

Theses

Slow dynamics in structured neural network models

S. P. Muscinelli / W. Gerstner (Dir.)  

Lausanne, EPFL, 2018. 

Model-based reinforcement learning and navigation in animals and machines

D. S. Corneil / W. Gerstner (Dir.)  

Lausanne, EPFL, 2018. 

One-shot learning and eligibility traces in sequential decision making

M. P. Lehmann / W. Gerstner; K. Preuschoff (Dir.)  

Lausanne, EPFL, 2018. 

2017

Journal Articles

Exponentially long orbits in Hopfield neural networks

S. P. Muscinelli; W. Gerstner; J. M. Brea 

Neural Computation. 2017. Vol. 29, num. 2, p. 458 – 484. DOI : 10.1162/NECO_a_00919.

2016

Journal Articles

Prospective Coding by Spiking Neurons

J. Brea; A. T. Gaal; R. Urbanczik; W. Senn 

Plos Computational Biology. 2016. Vol. 12, num. 6, p. e1005003. DOI : 10.1371/journal.pcbi.1005003.

Does computational neuroscience need new synaptic learning paradigms?

J. M. Brea; W. Gerstner 

Current Opinion in Behavioral Sciences. 2016. Vol. 11, p. 61 – 66. DOI : 10.1016/j.cobeha.2016.05.012.

Conference Papers

Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

F. Colombo; S. P. Muscinelli; A. Seeholzer; J. Brea; W. Gerstner 

2016. 1st Conference on Computer Simulation of Musical Creativity, University of Huddersfield, UK, 17 – 19 June 2016. DOI : 10.13140/RG.2.1.2436.5683.