paper-with-me

Papers

A Spacetime Perspective on Dynamical Computation in Neural Information Processing Systems

2024-09-20 · T. Anderson Keller, Lyle Muller, Terrence J. Sejnowski, Max Welling

There is now substantial evidence for traveling waves and other structured spatiotemporal recurrent neural dynamics in cortical structures; but these observations have typically been difficult to reconcile with notions of topographically organized selectivity and feedforward receptive fields. We introduce a new 'spacetime' perspective on neural computation in which structured selectivity and dynamics are not contradictory but instead are complimentary. We show that spatiotemporal dynamics may be a mechanism by which natural neural systems encode approximate visual, temporal, and abstract symmetries of the world as conserved quantities, thereby enabling improved generalization and long-term working memory.

📄 PDF Abstract BibTeX arXiv:2409.13669

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Machine-Learning the Classification of Spacetimes

2022-01-05 · Yang-Hui He, Juan Manuel Pérez Ipiña

On the long-established classification problems in general relativity we take a novel perspective by adopting fruitful techniques from machine learning and modern data-science. In particular, we model Petrov's classifica…

BIG-bench Machine LearningClassificationData VisualizationDimensionality Reduction

A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition

2017-08-22 · ICCV 2017 10 · Isma Hadji, Richard P. Wildes

This paper presents a novel hierarchical spatiotemporal orientation representation for spacetime image analysis. It is designed to combine the benefits of the multilayer architecture of ConvNets and a more controlled app…

Dynamic Texture Recognition

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

2020-08-06 · NeurIPS 2020 12 · Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic 외

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interroga…

Camera Pose EstimationObjectPose Estimation

On the Holographic Geometry of Deterministic Computation

2025-11-29 · Logan Nye arxiv

Standard simulations of Turing machines suggest a linear relationship between the temporal duration $t$ of a run and the amount of information that must be stored by known simulations to certify, verify, or regenerate th…

Agent Semantics, Semantic Spacetime, and Graphical Reasoning

2025-06-09 · Mark Burgess

Some formal aspects of the Semantic Spacetime graph model are presented, with reference to its use for directed knowledge representations and process modelling. A finite $\gamma(3,4)$ representation is defined to form a …