arXiv subjects

Peter Helfer

Publications and source records attributed to Peter Helfer.

4 recordsLinked to original sources

arXiv2024

TACOS: Task Agnostic Continual Learning in Spiking Neural Networks

Catastrophic interference, the loss of previously learned information when learning new information, remains a major challenge in machine learning. Since living organisms do not seem to suffer from this problem, researchers have taken inspiration from biology to improve memory retention in artificial intelligence systems. However, previous attempts to use bio-inspired mechanisms have typically resulted in systems that rely on task boundary information during training and/or explicit task identification during inference, information that is not available in real-world scenarios. Here, we show that neuro-inspired mechanisms such as synaptic consolidation and metaplasticity can mitigate catastrophic interference in a spiking neural network, using only synapse-local information, with no need for task awareness, and with a fixed memory size that does not need to be increased when training on new tasks. Our model, TACOS, combines neuromodulation with complex synaptic dynamics to enable new learning while protecting previous information. We evaluate TACOS on sequential image recognition tasks and demonstrate its effectiveness in reducing catastrophic interference. Our results show that TACOS outperforms existing regularization techniques in domain-incremental learning scenarios. We also report the results of an ablation study to elucidate the contribution of each neuro-inspired mechanism separately.

cs.NE↗

arXiv2019

Neural-network simulations of memory consolidation and reconsolidation

In the mammalian brain newly acquired memories depend on the hippocampus for maintenance and recall, but over time these functions are taken over by the neocortex through a process called systems consolidation. However, reactivation of a consolidated memory can induce a brief period of temporary hippocampus-dependence, followed by return to hippocampus-independence. Here we present a computational model that uses simulation of recently described mechanisms of synaptic plasticity to account for findings from the systems consolidation/reconsolidation literature and to make predictions for future research.

q-bio.NC↗

arXiv2017

Coupled feedback loops maintain synaptic long-term potentiation: A computational model of PKMzeta synthesis and AMPA receptor trafficking

In long-term potentiation (LTP), one of the most studied types of neural plasticity, synaptic strength is persistently increased in response to stimulation. Although a number of different proteins have been implicated in the sub-cellular molecular processes underlying induction and maintenance of LTP, the precise mechanisms remain unknown. A particular challenge is to demonstrate that a proposed molecular mechanism can provide the level of stability needed to maintain memories for months or longer, in spite of the fact that many of the participating molecules have much shorter life spans. Here we present a computational model that combines simulations of several biochemical reactions that have been suggested in the LTP literature and show that the resulting system does exhibit the required stability. At the core of the model are two interlinked feedback loops of molecular reactions, one involving the atypical protein kinase PKM{\zeta} and its messenger RNA, the other involving PKM{\zeta} and GluA2-containing AMPA receptors. We demonstrate that robust bistability - stable equilibria both in the synapse's potentiated and unpotentiated states - can arise from a set of simple molecular reactions. The model is able to account for a wide range of empirical results, including induction and maintenance of late-phase LTP, cellular memory reconsolidation and the effects of different pharmaceutical interventions.

q-bio.NC↗

arXiv2017

A Computational Model of Systems Memory Consolidation and Reconsolidation

In the mammalian brain, newly acquired memories depend on the hippocampus for maintenance and recall, but over time the neocortex takes over these functions, rendering memories hippocampus-independent. The process responsible for this transformation is called systems memory consolidation. However, reactivation of a well-consolidated memory can trigger a temporary return to a hippocampus-dependent state, a phenomenon known as systems memory reconsolidation. The neural mechanisms underlying systems memory consolidation and reconsolidation are not well understood. Here, we propose a neural model based on well-documented mechanisms of synaptic plasticity and stability and describe a computational implementation that demonstrates the model's ability to account for a range of findings from the systems consolidation and reconsolidation literature. We derive several predictions from the computational model and suggest experiments that may test its validity.

q-bio.NC↗