SNUFA 2022 Abstracts

Invited talks

• Merging insights from artificial and biological neural networks for neuromorphic intelligence, Charlotte Frenkel (TU Delft),
• Algorithm-Hardware Co-design for Efficient and Robust Spiking Neural Networks, Priya Panda (Yale),
• Why dendrites matter for biological and artificial circuits, Yiota Poirazi (Institute of Molecular Biology and Biotechnology IMBB),
• Spiking Deep Learning with SpikingJelly, Yonghong Tian (Peking University)

Contributed talks

• Behavioral Timescale Synaptic Plasticity (BTSP) for biologically plausible credit assignment across multiple layers via top-down gating of dendritic plasticity (A. Galloni, A. Peddada, A. Milstein)

• Beyond Biologically Plausible Spiking Networks for Neuromorphic Computing (Anand Subramoney, Khaleelulla Khan Nazeer, Mark Schöne, Christian Mayr, David Kappel)

• Training Dynamic Spiking Neural Network via Forward Propagation Through Time (Bojian Yin, Federico Corradi and Sander M Bohte)

• Bridging the gap between artificial models and cortical circuits (Christopher B. Currin, Karin Stecher, Carsten Pfeffer, Gaia Novarino, and Tim P. Vogels)

• Nonlinear computations in spiking neural networks through multiplicative synapses (Michele Nardin, James W Phillips, William F Podlaski, Sander W Keemink)

• Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity (Thomas Limbacher, Ozan Özdenizci, Robert Legenstein)

• Universal function approximation in balanced spiking networks through convex-concave boundary composition (William F Podlaski, Christian K Machens)

• A biologically plausible inhibitory plasticity rule for world-model learning in SNNs (Zhenrui Liao, Darian Hadjiabadi, Satoshi Terada, Ivan Soltesz, Attila Losonczy)

Posters

• Evaluating the temporal understanding of spiking neural networks on event-based action recognition with DVS-Gesture-Chain (Alex Vicente-Sola)

• Library of dynamics: linking parameters and behaviour of spiking networks with Simulation-Based Inference (Basile Confavreux, Aaradhya Vaze, Poornima Ramesh, Pedro Gonçalves, Jakob H. Macke and Tim P. Vogels)

• Neural Network for Modelling Ion Channels in Smooth Muscle Electrophysiology (Chitaranjan Mahapatra)

• Deriving STDP from Backpropagation (Nicholas Alonso, Felix Wang, Corinne Teeter)

• Optic Flow estimation from Event-based cameras and Spiking Neural Networks (CUADRADO Javier, RANÇON Ulysse, COTTEREAU Benoît, BARRANCO Francisco and MASQUELIER Timothée)

• Time Series Forecasting with Spiking Neural Networks (Davide L. Manna)

• Demonstrating a fully automated software framework for PyTorch-based training on BrainScaleS-2 using a high-speed data communication example (Elias Arnold, Eric Müller, Philipp Spilger)

• Varied Delays in Spiking Neural Networks Support Learning With Conjunctive Temporal Features (Felix Wang, Corinne Teeter)

• Synergistic short-term plasticity mechanisms for working memory (Florian Fiebig, Nikolaos Chrysanthidis, Anders Lansner, Pawel Herman)

• Hyperdimensional Computing Using Time-To-Spike Neuromorphic Circuits (Graham Bent, Christopher Simpkin, Yuhua Li, and Alun Preece ( Cardiff University, Cardiff, UK ))

• A coordinated spiking network model of the hippocampus accounts for remapping and inhibitory perturbations. (Guillermo Martín-Sánchez, William Podlaski, Christian K. Machens)

• Quantized Rewiring: Hardware-aware training of sparse deep neural networks (Horst Petschenig and Robert Legenstein)

• Mitigating Catastrophic Forgetting in Spiking Neural Networks through Threshold Modulation (Ilyass Hammouamri)

• Exploiting Sparsity for Accelerated SNN Training on Graphcore IPUs (Jan Finkbeiner, Emre Neftci)

• A protein-driven heterosynaptic rule for spiking neural networks (Janko Petkovic, Maximilian Eggl, Tatjana Tchumatchenko)

• Online Learning via Constrained Parameter Inference (COPI) (Jesús García Fernández)

• Cleo: a simulation testbed for bridging model and experiment in mesoscale neuroscience (Kyle Johnsen, Nathanael Cruzado, Adam Willats, Christopher Rozell)

• Gradient Computation and Analog Neuromorphic Hardware (Luca Blessing)

• Temporally shifted STDP rule reveals synapses crucial for learning (Maayan Levy, Tim P. Vogels)

• Design and Simulation of Spiking Programmable Neural Computers (Mehmet Kerem Turkcan)

• Historically Dependent NMDA-modulated Resonant Synapses for Decoding Time Structured Spike Trains (Nigel Crook, Alex Rast, Eleni Elia)

• Seeing Through Uncertainty with Spikes not Bayes (Paul Kirkland)

• Population geometry enables fast sampling in spiking neural networks (Paul Masset, Jacob A. Zavatone-Veth, J. Patrick Connor, Venkatesh N. Murthy and Cengiz Pehlevan)

• A spatiotemporally-resolved view of cellular contributions to chaos and information flow in spiking neural networks (Rainer Engelken, Fred Wolf)

• Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks (Samuel Schmidgall, Joe Hays, Maryam Parsa)

• Loss matters: Limitations of learning with exact gradients in SNNs (Thomas Nowotny, James P. Turner, James C. Knight)

• An Optimized Deep Spiking Neural Network Architecture Without Gradients (Yeshwanth Bethi, André van Schaik, and Saeed Afshar)