SparseProp: efficient event-based simulation and training of sparse recurrent spiking neural networks

R Engelken - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
Abstract Spiking Neural Networks (SNNs) are biologically-inspired models that are capable
of processing information in streams of action potentials. However, simulating and training …

Smooth Exact Gradient Descent Learning in Spiking Neural Networks

C Klos, RM Memmesheimer - arXiv preprint arXiv:2309.14523, 2023 - arxiv.org
Artificial neural networks are highly successfully trained with backpropagation. For spiking
neural networks, however, a similar gradient descent scheme seems prohibitive due to the …

[HTML][HTML] Purely STDP-based assembly dynamics: Stability, learning, overlaps, drift and aging

P Manz, RM Memmesheimer - PLOS Computational Biology, 2023 - journals.plos.org
Memories may be encoded in the brain via strongly interconnected groups of neurons,
called assemblies. The concept of Hebbian plasticity suggests that these assemblies are …

Stability of dynamics and memory in the balanced state

P Manz - 2023 - bonndoc.ulb.uni-bonn.de
Computational modeling of neural circuits has successfully explained the observed irregular
and asynchronous activity in the brain as the result of a dynamical balance of excitatory and …

[PDF][PDF] Complex Dynamics Enabled by Basic Neural Features

D Regel - 2020 - ediss.uni-goettingen.de
The human brain is considered by many to be the most complex object we know. It enables
us to perceive, to think, to feel and to interact with the world. Understanding how the brain …