Cargando…
Learning cortical hierarchies with temporal Hebbian updates
A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations....
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10244748/ https://www.ncbi.nlm.nih.gov/pubmed/37293353 http://dx.doi.org/10.3389/fncom.2023.1136010 |
_version_ | 1785054711948247040 |
---|---|
author | Aceituno, Pau Vilimelis Farinha, Matilde Tristany Loidl, Reinhard Grewe, Benjamin F. |
author_facet | Aceituno, Pau Vilimelis Farinha, Matilde Tristany Loidl, Reinhard Grewe, Benjamin F. |
author_sort | Aceituno, Pau Vilimelis |
collection | PubMed |
description | A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations. Similar hierarchical structures routinely emerge in artificial neural networks (ANNs) trained for object recognition tasks, suggesting that similar structures may underlie biological neural networks. However, the classical ANN training algorithm, backpropagation, is considered biologically implausible, and thus alternative biologically plausible training methods have been developed such as Equilibrium Propagation, Deep Feedback Control, Supervised Predictive Coding, and Dendritic Error Backpropagation. Several of those models propose that local errors are calculated for each neuron by comparing apical and somatic activities. Notwithstanding, from a neuroscience perspective, it is not clear how a neuron could compare compartmental signals. Here, we propose a solution to this problem in that we let the apical feedback signal change the postsynaptic firing rate and combine this with a differential Hebbian update, a rate-based version of classical spiking time-dependent plasticity (STDP). We prove that weight updates of this form minimize two alternative loss functions that we prove to be equivalent to the error-based losses used in machine learning: the inference latency and the amount of top-down feedback necessary. Moreover, we show that the use of differential Hebbian updates works similarly well in other feedback-based deep learning frameworks such as Predictive Coding or Equilibrium Propagation. Finally, our work removes a key requirement of biologically plausible models for deep learning and proposes a learning mechanism that would explain how temporal Hebbian learning rules can implement supervised hierarchical learning. |
format | Online Article Text |
id | pubmed-10244748 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-102447482023-06-08 Learning cortical hierarchies with temporal Hebbian updates Aceituno, Pau Vilimelis Farinha, Matilde Tristany Loidl, Reinhard Grewe, Benjamin F. Front Comput Neurosci Neuroscience A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations. Similar hierarchical structures routinely emerge in artificial neural networks (ANNs) trained for object recognition tasks, suggesting that similar structures may underlie biological neural networks. However, the classical ANN training algorithm, backpropagation, is considered biologically implausible, and thus alternative biologically plausible training methods have been developed such as Equilibrium Propagation, Deep Feedback Control, Supervised Predictive Coding, and Dendritic Error Backpropagation. Several of those models propose that local errors are calculated for each neuron by comparing apical and somatic activities. Notwithstanding, from a neuroscience perspective, it is not clear how a neuron could compare compartmental signals. Here, we propose a solution to this problem in that we let the apical feedback signal change the postsynaptic firing rate and combine this with a differential Hebbian update, a rate-based version of classical spiking time-dependent plasticity (STDP). We prove that weight updates of this form minimize two alternative loss functions that we prove to be equivalent to the error-based losses used in machine learning: the inference latency and the amount of top-down feedback necessary. Moreover, we show that the use of differential Hebbian updates works similarly well in other feedback-based deep learning frameworks such as Predictive Coding or Equilibrium Propagation. Finally, our work removes a key requirement of biologically plausible models for deep learning and proposes a learning mechanism that would explain how temporal Hebbian learning rules can implement supervised hierarchical learning. Frontiers Media S.A. 2023-05-24 /pmc/articles/PMC10244748/ /pubmed/37293353 http://dx.doi.org/10.3389/fncom.2023.1136010 Text en Copyright © 2023 Aceituno, Farinha, Loidl and Grewe. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Aceituno, Pau Vilimelis Farinha, Matilde Tristany Loidl, Reinhard Grewe, Benjamin F. Learning cortical hierarchies with temporal Hebbian updates |
title | Learning cortical hierarchies with temporal Hebbian updates |
title_full | Learning cortical hierarchies with temporal Hebbian updates |
title_fullStr | Learning cortical hierarchies with temporal Hebbian updates |
title_full_unstemmed | Learning cortical hierarchies with temporal Hebbian updates |
title_short | Learning cortical hierarchies with temporal Hebbian updates |
title_sort | learning cortical hierarchies with temporal hebbian updates |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10244748/ https://www.ncbi.nlm.nih.gov/pubmed/37293353 http://dx.doi.org/10.3389/fncom.2023.1136010 |
work_keys_str_mv | AT aceitunopauvilimelis learningcorticalhierarchieswithtemporalhebbianupdates AT farinhamatildetristany learningcorticalhierarchieswithtemporalhebbianupdates AT loidlreinhard learningcorticalhierarchieswithtemporalhebbianupdates AT grewebenjaminf learningcorticalhierarchieswithtemporalhebbianupdates |