Synaptic Delay

Synaptic delay, the time it takes for a signal to travel between neurons, significantly impacts neural network function and learning. Current research focuses on incorporating and learning these delays within various neural network models, including spiking neural networks (SNNs) and neural delay differential equations (NDDEs), often using backpropagation-through-time and novel gradient calculation methods. This work aims to improve model accuracy, energy efficiency, and biological realism, particularly in applications involving temporal data processing like speech recognition and neuromorphic computing. The ability to accurately model and leverage synaptic delays promises advancements in both our understanding of biological neural systems and the development of more efficient and powerful artificial neural networks.

Papers

October 3, 2024

Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems
Thibault Monsel, Emmanuel Menier, Onofrio Semeraro, Lionel Mathelin, Guillaume Charpiat
Dynamical System Scientific Hypothesis Neural CDEs Experimental Data Synaptic Delay Delay Differential Equation

September 17, 2024

Inferno: An Extensible Framework for Spiking Neural Networks
Marissa Dominijanni
Neural Network Pytorch Model Spike Timing Dependent Plasticity Extensible Framework Secret Key Synaptic Delay

August 17, 2024

A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations
Housen Wang, Yuxing Chen, Sirong Cao, Xiaoli Wang, Qiang Liu
Deep Neural Network Inverse Problem Differential Equation Deep Learning Framework Synaptic Delay Delay Differential Equation

July 7, 2024

May 27, 2024

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
Mingqing Xiao, Yixin Zhu, Di He, Zhouchen Lin
Graph Reasoning Neural Computation Synaptic Delay Multi Path Temporal Encoding

April 30, 2024

DelGrad: Exact gradients in spiking networks for learning transmission delays and weights
Julian Göltz, Jimmy Weber, Laura Kriener, Peter Lake, Melika Payvand, Mihai A. Petrovici
Neural Network Network Programming Balancing Weight Synaptic Feedback Synaptic Weight Synaptic Delay Communication Delay Exact Gradient BrainScaleS 2

April 16, 2024

Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors
Alberto Patino-Saucedo, Roy Meijer, Amirreza Yousefzadeh, Manil-Dev Gomony, Federico Corradi, Paul Detteter, Laura Garrido-Regife, Bernabe Linares-Barranco, Manolis Sifalakis
Full Model Synaptic Delay Neuromorphic Platform Hardware Aware Training Core Neuromorphic

March 29, 2024

Data-Driven Room Acoustic Modeling Via Differentiable Feedback Delay Networks With Learnable Delay Lines
Alessandro Ilic Mezza, Riccardo Giampiccolo, Enzo De Sena, Alberto Bernardini
Loss Function Delayed Feedback Room Acoustic Time Delay Synaptic Delay Reverberation Time

February 27, 2024

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
Ruizhe Zhong, Junjie Ye, Zhentao Tang, Shixiong Kai, Mingxuan Yuan, Jianye Hao, Junchi Yan
Pre Training Attention Model Large Scale Circuit Timing Analysis Synaptic Delay Circuit Representation

November 17, 2023

On exploiting the synaptic interaction properties to obtain frequency-specific neurons
Guillaume Marthe, Claire Goursaud, Romain Cazé, Laurent Clavier
Circuit Design Spike Timing Synaptic Connectivity Synaptic Delay Analog Computing Task Specific Neuron

October 29, 2023

Expanding memory in recurrent spiking networks
Ismael Balafrej, Fabien Alibart, Jean Rouat
Network Programming Memory Trace Neuromorphic Processor Synaptic Delay Recurrent Connection

September 12, 2023

Co-learning synaptic delays, weights and adaptation in spiking neural networks
Lucas Deckers, Laurens Van Damme, Ing Jyh Tsang, Werner Van Leekwijck, Steven Latré
Neural Network Adaptation Concern Neuromorphic Hardware Balancing Weight Spike Based Spike Camera Synaptic Delay

June 9, 2023

Beyond Weights: Deep learning in Spiking Neural Networks with pure synaptic-delay training
Edoardo W. Grappolini, Anand Subramoney
Neural Network Deep Learning Spiking Neural Network Back Propagation Balancing Weight Synaptic Weight Synaptic Delay

February 16, 2023

Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition
Pengfei Sun, Ehsan Eqlimi, Yansong Chua, Paul Devos, Dick Botteldooren
Neural Network Transformer Feed Forward Layer Synaptic Delay Spike Encoding Word Recognition

January 15, 2023

Generalized Neural Closure Models with Interpretability
Abhinav Gupta, Pierre F. J. Lermusiaux
Inherent Interpretability Differentiable Physic Dynamical Model Fidelity Model Synaptic Delay Closure Model

July 29, 2022

Significant changes in EEG neural oscillations during different phases of three-dimensional multiple object tracking task (3D-MOT) imply different roles for attention and working memory
Yannick Roy, Jocelyn Faubert
Memory Trace Multiple Object Tracking 3D Model 3D Multi Object Tracking Working Memory Electroencephalography Recording Synaptic Delay Neural Oscillation

April 20, 2022

Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks
Pengfei Sun, Longwei Zhu, Dick Botteldooren
Neuromorphic Datasets Short Term Memory Spike Timing Synaptic Delay Biological Neuron Deep Spiking Neural Network

Synaptic Delay

Papers

Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems

Inferno: An Extensible Framework for Spiking Neural Networks

A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations

Prospective Messaging: Learning in Networks with Communication Delays

Learning Delays Through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

DelGrad: Exact gradients in spiking networks for learning transmission delays and weights

Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors

Data-Driven Room Acoustic Modeling Via Differentiable Feedback Delay Networks With Learnable Delay Lines

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling

On exploiting the synaptic interaction properties to obtain frequency-specific neurons

Expanding memory in recurrent spiking networks

Co-learning synaptic delays, weights and adaptation in spiking neural networks

Beyond Weights: Deep learning in Spiking Neural Networks with pure synaptic-delay training

Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition

Generalized Neural Closure Models with Interpretability

Significant changes in EEG neural oscillations during different phases of three-dimensional multiple object tracking task (3D-MOT) imply different roles for attention and working memory

Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks