SNUFA 2025 Abstracts

Click here for the full programme

Talk

• Space as Time Through Neuron Position Learning (Balázs Mészáros, James C. Knight, Thomas Nowotny, Danyal Akarca)
• Assembly-based computations through contextual dendritic gating of plasticity (Sebastian Onasch, Christoph Miehl, M. Maurycy Miękus, Julijana Gjorgjieva)
• Synaptic Plasticity Shapes Triplet Connectivity Motifs in Spiking Networks (Claudia Cusseddu, Dylan Festa, Christoph Miehl, Julijana Gjorgjieva)
• Spiking Differential Equation Solvers: A Minimal Framework for Dynamical Computation (Manoj N H, Avisha Mathur, Aryan Jain, Keshav Garodia, Veeranatesan S)
• Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays (Marissa Dominijanni, Alexander Ororbia, Kenneth W. Regan)
• Spiking neurons as predictive controllers of linear systems (Paolo Agliati, André Urbano, Pablo Lanillos, Nasir Ahmad, Marcel van Gerven, Sander Keemink)
• Emergence and maintenance of modularity in neural networks with Hebbian and anti-Hebbian inhibitory STDP (Raphaël Bergoin, Alessandro Torcini, Gustavo Deco, Mathias Quoy, Gorka Zamora-López)

Flash talk

• Memory capacity in spiking neural networks with fixed synaptic weight distribution (Aaradhya Vaze, Maayan Levy, Tim P. Vogels )
• Neuromodulation enhances dynamic sensory processing in spiking neural network models (AbdelQader AlKilany, Dan Goodman)
• Energy-Based and Transformer Models for Neural Circuit Modeling (Abolfazl HaqiqiFar, Reza Jafari)
• Asynchrony as a substitute for chaos in training ring spiking neural networks (Afroditi Talidou, Wilten Nicola)
• Single Spiking Neural Network with Neuromodulated Attractors for Adaptive Robotic Quadruped Gait Switching (Gabriel Torre, Juan Giribet, Sergio Lew)
• Exploring Information-Constrained Latent Spaces in Adaptive Spiking Neural Networks (Jhon Intriago, Pablo A. Estévez)
• Emerging assembly structures in trained spiking neural networks (Julia Gygax, Friedemann Zenke)
• Exploiting heterogeneous delays for efficient computation in low-bit neural networks (Pengfei Sun, Dan Goodman, Danyal Akarca)
• Neural Heterogeneity Enables Adaptive Encoding of Time Sequences (Raphaël Lafond-Mercier, Leonard Maler, Avner Wallach, André Longtin)
• Spikes can transmit neurons’ subthreshold membrane potentials (Valentin Schmutz)

Poster

• Information-Theoretic Graph Neural Networks for Modeling Brain Connectivity (Abolfazl HaqiqiFar, Majid Saberi, Reza Jafari)
• Probabilistic Inference of Precise Spiking Motifs (Adrien Fois, Laurent Perrinet)
• Noradrenergic-inspired gain modulation attenuates the stability gap in joint training (Alejandro Rodriguez-Garcia , Anindya Ghosh, Srikanth Ramaswamy)
• DelRec: learning delays in recurrent spiking neural networks. (Alexandre Queant, Ulysse Rançon, Benoit R Cotterau, Timothée Masquelier)
• Anticipation in Multi-Agent Systems: A Dynamical Systems Approach to Self-Coordination (Ali Baokbah, Iran Roman, Ji Chul Kim, Edward Large)
• Dynamical Analysis Of The Role Of Synaptic Dynamics In Coupled Neural Populations (Ana Mayora-Cebollero, Roberto Barrio, Jorge A. Jover-Galtier, Carmen Mayora-Cebollero, Lucía Pérez, Sergio Serrano)
• A Unified Cross-Domain Software Framework for Interfacing with Biological, Virtual, and Neuromorphic Spiking Neuronal Networks (Andrey Formozov, Liam Keegan, Harald Mack, James S. Bowyer, J. Simon Wiegert )
• Hybrid Spiking–Kolmogorov–Arnold Networks (Andrii Krutsylo)
• Exploring the Inner Workings and Internal Representations of Predictive Coding Networks in Comparison to Usual Feedforward Neural Networks (Aslan Satary Dizaji)
• Stereo processing in the human brain in the light of the superposition theory (Bayu Gautama Wundari, Ichiro Fujita, Hiroshi Ban)
• Neuronal heterogeneity of normalization strength in a circuit model (Deying Song, Douglas Ruff, Marlene Cohen, Chengcheng Huang)
• Quantum-Inspired Neuromorphic Modeling of Action Potentials at the Edge for Bio-Inspired AI (Chitaranjan Mahapatra, Ashish Kumar Pradhan)
• Low dimensional dynamics of a sparse balanced synaptic network of quadratic integrate-and-fire neurons (Denis S. Goldobin, Maria V. Ageeva)
• Causal pieces: analysing and improving spiking neural networks piece by piece (Dominik Dold, Philipp Petersen)
• Distributed engrams enable parallelized orthogonal computations within and across brain regions (Douglas Feitosa Tomé, Chenchen Shen, Basile Confavreux, Madhumathan Mukherjee, Ying Zhang, Dheeraj S. Roy, Tim P. Vogels)
• A local homeostatic STDP rule for stable dynamics and stimulus selectivity in recurrent spiking neural networks (Dylan Festa, Claudia Cusseddu, Divyansh Gupta, Julijana Gjorgjieva )
• Hardware multichannel time encoding with leaky integrate-and-fire neurons (Alessandro Macuglia, Giacomo Indiveri)
• Solving constrained minimax problems with spiking neural networks (Guillermo Martín-Sánchez, William F. Podlaski, Christian K. Machens)
• A genetic algorithm for self-supervised models of oscillatory neurodynamics (Jason Sherfey, Andre Bastos)
• Inferring response times of perceptual decisions with Poisson variational autoencoders (Hayden R. Johnson, Anastasia N. Krouglova, Hadi Vafaii, Jacob L. Yates, Pedro J. Goncalves)
• Deep-learning-assisted simulation of a cortical circuit: Integrating anatomy, physiology and function (Shinya Ito, Darrell Haufler, Javier Galván Fraile, Kael Dai, Joe Aman, Omid Zobeiri, Guozhang Chen, Claudio Mirraso, Wolfgang Maass, and Anton Arkhipov)
• Addressing the Comparability Crisis in Adaptive SNNs (Jhon Intriago, Pablo A. Estévez)
• Hyperparameter Estimation to Improve Spiking Neural Networks’ Learning (Jhon Intriago, Pablo A. Estévez)
• A spiking implementation of the incentive circuit model for mushroom body learning and behavior (Jordan Watts, Barbara Webb)
• On the geometry of recurrent spiking networks (Josue Casco-Rodriguez)
• Versatile Learning in Neural Networks Without Synaptic Plasticity (Kai Mason, Sonia Sennik, Claudia Clopath, Aaron Gruber, and Wilten Nicola)
• Reducing computational cost in spiking networks with a periodic reset model (Marco Tasca, Julia Gygax, Friedemann Zenke)
• Novel Deep-RL Method for Three-Factor Based Automata (Michael Tarlton)
• Exploring the Generalizability of Directly Connected Hybrid Spiking-Nonspiking Neural Networks (Nalini Ramanathan, Maren Eberle, Erdem Varol)
• Evolving reward-driven synaptic learning rules in Spiking Neural Networks for simple RL tasks (Napat Sahapat, Yeshwanth Bethi, Sergio Chevtchenko, Saeed Afshar)
• Demonstrating Universal Approximation with a Biophysically Faithful Hodgkin–Huxley Engine (Nicholas Windley, Desmond Atkins )
• Mean Field Analysis of a Stochastic STDP model (Pascal Helson, Etienne Tanré, Romain Veltz)
• Robustness of Spike-Based Computations Across Temporal Resolutions (Prakriti Parthasarathy, Timothy O’Leary)
• BurstFormer: a spiking Transformer trained with biologically inspired learning rules (Xingyun Wang,Richard Naud)
• Thalamic Hyperconnectivity and Functional Signatures in fMRI Connectomes of Autism Spectrum Disorder (S M Shayez karim, R S Rathore)
• Multiple-Output Spiking Neurons with Generalized Reset Feedback Mechanisms (Sanja Karilanova, Subhrakanti Dey, Ayça Özçelikkale)
• EFLOP: a sparsity-aware metric for evaluating computational cost (Simon Narduzzi, Friedemann Zenke, Shih-Chii Liu, L Andrea Dunbar)
• Detection of spiking motifs of arbitrary length in neural activity using bounded synaptic delays (Thomas Kronland-Martinet, Stéphane Viollet, Laurent Perrinet)
• Learning in Spiking Neural Networks: A Backpropagation-Compatible Architecture Using Conductance Neurons (Navid Akbari, Kai Mason, Aaron Gruber, Wilten Nicola)
• e-prop based SNN for handwritten character generation (Marc Pomar, Aksel Serret, Alicia Fornes, Xavier Otazu)
• State-space models can learn in-context by gradient descent (Yudou Tian, Neeraj Mohan Sushma, Nicolo Colombo, David Kappel, Anand Subramoney)