Determinantal point process attention over grid cell code supports out of distribution generalization

一般化 计算机科学 网格 人工智能 理论计算机科学 编码(集合论) 集合(抽象数据类型) 数学 数学分析 几何学 程序设计语言
作者
Shanka Subhra Mondal,Steven Frankland,Taylor W. Webb,Jonathan D. Cohen
出处
期刊:eLife [eLife Sciences Publications Ltd]
卷期号:12 被引量:1
标识
DOI:10.7554/elife.89911.3
摘要

Deep neural networks have made tremendous gains in emulating human-like intelligence, and have been used increasingly as ways of understanding how the brain may solve the complex computational problems on which this relies. However, these still fall short of, and therefore fail to provide insight into how the brain supports strong forms of generalization of which humans are capable. One such case is out-of-distribution (OOD) generalization – successful performance on test examples that lie outside the distribution of the training set. Here, we identify properties of processing in the brain that may contribute to this ability. We describe a two-part algorithm that draws on specific features of neural computation to achieve OOD generalization, and provide a proof of concept by evaluating performance on two challenging cognitive tasks. First we draw on the fact that the mammalian brain represents metric spaces using grid cell code (e.g., in the entorhinal cortex): abstract representations of relational structure, organized in recurring motifs that cover the representational space. Second, we propose an attentional mechanism that operates over the grid cell code using determinantal point process (DPP), that we call DPP attention (DPP-A) – a transformation that ensures maximum sparseness in the coverage of that space. We show that a loss function that combines standard task-optimized error with DPP-A can exploit the recurring motifs in the grid cell code, and can be integrated with common architectures to achieve strong OOD generalization performance on analogy and arithmetic tasks. This provides both an interpretation of how the grid cell code in the mammalian brain may contribute to generalization performance, and at the same time a potential means for improving such capabilities in artificial neural networks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
欢呼的丁真完成签到,获得积分10
刚刚
1秒前
沐青给Eber的求助进行了留言
3秒前
4秒前
hottest发布了新的文献求助10
5秒前
5秒前
5秒前
baifeng完成签到,获得积分10
5秒前
6秒前
科目三应助洵音采纳,获得10
8秒前
jxx完成签到 ,获得积分10
9秒前
SYLH应助hottest采纳,获得10
10秒前
XM完成签到 ,获得积分10
10秒前
小白发布了新的文献求助10
10秒前
10秒前
兴奋芷发布了新的文献求助10
12秒前
jn发布了新的文献求助10
12秒前
李健应助slby采纳,获得10
13秒前
15秒前
17秒前
小二郎应助nicolaslcq采纳,获得10
18秒前
干净的时光完成签到,获得积分10
18秒前
bobo完成签到 ,获得积分10
19秒前
wfy完成签到,获得积分10
19秒前
沐青应助123456采纳,获得50
20秒前
21秒前
可爱的鬼神完成签到,获得积分10
23秒前
mi完成签到,获得积分10
24秒前
jn完成签到,获得积分10
25秒前
25秒前
26秒前
南宫书瑶完成签到,获得积分10
26秒前
slby发布了新的文献求助10
26秒前
炸鸡完成签到,获得积分10
26秒前
有魅力的涵雁完成签到,获得积分10
28秒前
桐桐应助落后志泽采纳,获得10
28秒前
29秒前
沐青给Eber的求助进行了留言
30秒前
汤飞柏发布了新的文献求助20
32秒前
北北发布了新的文献求助20
32秒前
高分求助中
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3964581
求助须知:如何正确求助?哪些是违规求助? 3510110
关于积分的说明 11151469
捐赠科研通 3244224
什么是DOI,文献DOI怎么找? 1792341
邀请新用户注册赠送积分活动 873776
科研通“疑难数据库(出版商)”最低求助积分说明 803932