Memory Encoding Model

Huzheng Yang, James Gee, Jianbo Shi
8/2/2023
cs.CV

No official code found. Best implementation: huzeyann/MemoryEncodingModel (60 stars, last commit 2023-12-22).

Abstract

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 the non-visual brain is largely predictable using previously seen images. Our Memory Encoding Model (Mem) won the Algonauts 2023 visual brain competition even without model ensemble (single model score 66.8, ensemble score 70.8). Our ensemble model without memory input (61.4) can also stand a 3rd place. Furthermore, we observe periodic delayed brain response correlated to 6th-7th prior image, and hippocampus also showed correlated activity timed with this periodicity. We conjuncture that the periodic replay could be related to memory mechanism to enhance the working memory.

View on arXivView PDF

Code Implementations(1)

huzeyann/MemoryEncodingModelCommunity100%

[Algonauts 2023] PyTorch implementation of "Memory Encoding Model"

602Shell, PythonAug 2, 20232 years agoNOASSERTION

Similar Papers

A Biologically Inspired Visual Working Memory for Deep Networks

84% match1 repo212019

BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding

84% match2025

Neural Encoding for Image Recall: Human-Like Memory

84% match2024

Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior

82% match1 repo882025

Classification and Generation of real-world data with an Associative Memory Model

82% match2022

Retinotopy Inspired Brain Encoding Model and the All-for-One Training Recipe

82% match2023

Cite this paper

@article{yang2023memory,
  title  = {Memory Encoding Model},
  author = {Huzheng Yang and James Gee and Jianbo Shi},
  year   = {2023},
  eprint = {2308.01175},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.01175v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.01175.svg)](https://codeofpaper.com/paper/2308.01175)

Discussion