paper-with-me

Papers

Key-value memory in the brain

2025-01-06 · Samuel J. Gershman, Ila Fiete, Kazuki Irie

Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimonious, these models do not allow distinct representations for storage and retrieval, despite their distinct computational demands. Key-value memory systems, in contrast, distinguish representations used for storage (values) and those used for retrieval (keys). This allows key-value memory systems to optimize simultaneously for fidelity in storage and discriminability in retrieval. We review the computational foundations of key-value memory, its role in modern machine learning systems, related ideas from psychology and neuroscience, applications to a number of empirical puzzles, and possible biological implementations.

📄 PDF Abstract BibTeX arXiv:2501.02950

Code (1)

kazuki-irie/kv-memory-brain 공식 구현 pytorch

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Eigen Values Features for the Classification of Brain Signals corresponding to 2D and 3D Educational Contents

2019-04-30 · Saeed Bamatraf, Muhammad Hussain, Emad-ul-Haq Qazi, Hatim AboAlSamh

In this paper, we have proposed a brain signal classification method, which uses eigenvalues of the covariance matrix as features to classify images (topomaps) created from the brain signals. The signals are recorded dur…

General ClassificationMultiple-choice

Differential EEG Characteristics during Working Memory Encoding and Re-encoding

2021-12-13 · Gi-Hwan Shin, Young-Seok Kweon

Many studies have discussed the difference in brain activity related to encoding and retrieval of working memory (WM) tasks. However, it remains unclear if there is a change in brain activation associated with re-encodin…

EEGElectroencephalogram (EEG)Retrieval

Binarization Methods for Motor-Imagery Brain-Computer Interface Classification

2020-10-14 · Michael Hersche, Luca Benini, Abbas Rahimi

Successful motor-imagery brain-computer interface (MI-BCI) algorithms either extract a large number of handcrafted features and train a classifier, or combine feature extraction and classification within deep convolution…

BinarizationBrain Computer InterfaceClassificationGeneral Classification+1

Memory Encoding Model

2023-08-02 · Huzheng Yang, James Gee, Jianbo Shi

We explore a new class of brain encoding model by adding memory-related information as input. Memory is an essential brain mechanism that works alongside visual stimuli. During a vision-memory cognitive task, we found th…

Brain DecodingHippocampusmodel

Decoding finger flexion from band-specific ECoG signals in humans

2012-06-28 · Frontiers in Neuroscience, Section Neuroprosthetics 2012 6 · Nanying Liang, Laurent Bougrain

This article presents the method that won the brain-computer interface (BCI) competition IV addressed to the prediction of the finger flexion from electrocorticogram (ECoG) signals. ECoG-based BCIs have recently drawn th…

Brain Computer InterfaceBrain DecodingEEGElectroencephalogram (EEG)