4.6 Article

Biologically plausible local synaptic learning rules robustly implement deep supervised learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs

Beren Millidge et al.

Summary: Backpropagation of error can be approximated using predictive coding, a biologically plausible process theory of cortical computation. This result allows for the translation of core machine learning architectures into predictive coding equivalents, which perform equivalently to backprop on challenging machine learning benchmarks using only local and Hebbian plasticity.

NEURAL COMPUTATION (2022)

Article Multidisciplinary Sciences

Developmental and evolutionary constraints on olfactory circuit selection

Naoki Hiratani et al.

Summary: This study investigates the relationship between neural circuit structure and learning efficiency by analyzing the olfactory system. The results suggest that optimal neural architecture is influenced by the species' longevity and the genetic specification of the olfactory circuit.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2022)

Article Neurosciences

A gradual temporal shift of dopamine responses mirrors the progression of temporal difference error in machine learning

Ryunosuke Amo et al.

Summary: The authors have discovered that dopamine signals gradually move from the time of reward to the time of cue, similar to the evaluation signals used in temporal difference learning. This finding bridges the gap between computational theories and the brain, and provides fundamental insights into how the brain associates cues and rewards that are separated in time.

NATURE NEUROSCIENCE (2022)

Article Neurosciences

Impaired sharp-wave ripple coordination between the medial entorhinal cortex and hippocampal CA1 of knock-in model of Alzheimer's disease

Tsukasa Funane et al.

Summary: Clinical evidence suggests that disruptions in the coordination of sharp-wave ripples (SWRs) between the entorhinal cortex and hippocampal CA1 may serve as an early network symptom that precedes memory impairment in Alzheimer's disease. This study found that the coordination of SWRs between the medial entorhinal cortex (MEC) layers and CA1 was disrupted in amyloid precursor protein knock-in (APP-KI) mice, even before the emergence of spatial memory impairments. These findings provide insight into the underlying brain circuit mechanisms of memory impairments in Alzheimer's disease.

FRONTIERS IN SYSTEMS NEUROSCIENCE (2022)

Article Neurosciences

Reconciling neuronal representations of schema, abstract task structure, and categorization under cognitive maps in the entorhinal-hippocampal-frontal circuits

Kei M. Igarashi et al.

Summary: Learning leads to the formation of neuronal representations of acquired knowledge, traditionally referred to as cognitive maps in the hippocampus. Recent research has expanded this framework to include non-spatial memory and discovered similar knowledge representations in the entorhinal cortex and frontal cortex.

CURRENT OPINION IN NEUROBIOLOGY (2022)

Article Multidisciplinary Sciences

Dopamine facilitates associative memory encoding in the entorhinal cortex

Jason Y. Lee et al.

Summary: Mounting evidence suggests that dopamine plays a critical role in encoding cue-reward association rules in layer 2a fan cells of the lateral entorhinal cortex (LEC), and sends novelty-induced reward expectation signals to the LEC. Inhibition of LEC dopamine signals disrupts associative encoding of fan cells and impairs learning performance.

NATURE (2021)

Article Neurosciences

Learning Without Feedback: Fixed Random Learning Signals Allow for Feedforward Training of Deep Neural Networks

Charlotte Frenkel et al.

Summary: The direct random target projection (DRTP) algorithm proposed in this work views one-hot-encoded labels in supervised classification problems as a proxy for error signs, enabling layerwise feedforward training of hidden layers to solve weight transport and update locking issues while reducing computational and memory requirements.

FRONTIERS IN NEUROSCIENCE (2021)

Review Neurosciences

Backpropagation and the brain

Timothy P. Lillicrap et al.

NATURE REVIEWS NEUROSCIENCE (2020)

Article Biochemistry & Molecular Biology

A Unified Framework for Dopamine Signals across Timescales

HyungGoo R. Kim et al.

Article Neurosciences

A deep learning framework for neuroscience

Blake A. Richards et al.

NATURE NEUROSCIENCE (2019)

Review Neurosciences

Gamma oscillations in the entorhinal-hippocampal circuit underlying memory and dementia

Tomoaki Nakazono et al.

NEUROSCIENCE RESEARCH (2018)

Article Mathematical & Computational Biology

Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation

Benjamin Scellier et al.

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE (2017)

Article Neurosciences

Impaired In Vivo Gamma Oscillations in the Medial Entorhinal Cortex of Knock-in Alzheimer Model

Tomoaki Nakazono et al.

FRONTIERS IN SYSTEMS NEUROSCIENCE (2017)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Article Neurosciences

The entorhinal map of space

Kei M. Igarashi

BRAIN RESEARCH (2016)

Article Neurosciences

Dopamine neurons share common response function for reward prediction error

Neir Eshel et al.

NATURE NEUROSCIENCE (2016)

Article Multidisciplinary Sciences

Random synaptic feedback weights support error backpropagation for deep learning

Timothy P. Lillicrap et al.

NATURE COMMUNICATIONS (2016)

Review Neurosciences

Plasticity in oscillatory coupling between hippocampus and cortex

Kei M. Igarashi

CURRENT OPINION IN NEUROBIOLOGY (2015)

Article Multidisciplinary Sciences

Arithmetic and local circuitry underlying dopamine prediction errors

Neir Eshel et al.

NATURE (2015)

Review Computer Science, Artificial Intelligence

Deep learning in neural networks: An overview

Juergen Schmidhuber

NEURAL NETWORKS (2015)

Review Neurosciences

Coding and Transformations in the Olfactory System

Naoshige Uchida et al.

ANNUAL REVIEW OF NEUROSCIENCE, VOL 37 (2014)

Article Multidisciplinary Sciences

Coordination of entorhinal-hippocampal ensemble activity during associative learning

Kei M. Igarashi et al.

NATURE (2014)

Article Neurosciences

Olfactory cortical neurons read out a relative time code in the olfactory bulb

Rafi Haddad et al.

NATURE NEUROSCIENCE (2013)

Article Computer Science, Artificial Intelligence

Extreme learning machine: Theory and applications

Guang-Bin Huang et al.

NEUROCOMPUTING (2006)

Article Computer Science, Artificial Intelligence

Rate models for conductance-based cortical neuronal networks

O Shriki et al.

NEURAL COMPUTATION (2003)