Yorie Nakahira,Quanying Liu,Xiyu Deng et al.
Yorie Nakahira et al.
Human sensorimotor control is remarkably fast and accurate at the system level despite severe speed-accuracy trade-offs at the component level. The discrepancy between the contrasting speed-accuracy trade-offs at these two levels is a parad...
Anoop Praturu,Tatyana O Sharpee
Anoop Praturu
Matrix factorization is a central paradigm in matrix completion and collaborative filtering. Low-rank factorizations have been extremely successful in reconstructing and generalizing high-dimensional data in a wide variety of machine learni...
Transformer Models for Signal Processing: Scaled Dot-Product Attention Implements Constrained Filtering [0.03%]
信号处理的变换模型：缩放点积注意力实现约束滤波
Terence D Sanger
Terence D Sanger
The remarkable success of the transformer machine learning architecture for processing language sequences far exceeds the performance of classical signal processing methods. A unique component of transformer models is the scaled dot-product...
Rapid Reweighting of Sensory Inputs and Predictions in Visual Perception [0.03%]
视觉感知中感觉输入和预测的快速重新加权
William Turner,Oh-Sang Kwon,Minwoo J B Kim et al.
William Turner et al.
A striking perceptual phenomenon has recently been described wherein people report seeing abrupt jumps in the location of a smoothly moving object ("position resets"). Here, we show that this phenomenon can be understood within the framewor...
Encoding of Numerosity With Robustness to Object and Scene Identity in Biologically Inspired Object Recognition Networks [0.03%]
生物启发式物体识别网络中具有较强对象和场景身份抗性的数量编码
Thomas Chapalain,Bertrand Thirion,Evelyn Eger
Thomas Chapalain
Number sense, the ability to rapidly estimate object quantities in a visual scene without precise counting, is a crucial cognitive capacity found in humans and many other animals. Recent studies have identified artificial neurons tuned to n...
Firing Rate Models as Associative Memory: Synaptic Design for Robust Retrieval [0.03%]
基于发放率模型的联想记忆中的突触设计及稳健检索性能
Simone Betteti,Giacomo Baggio,Francesco Bullo et al.
Simone Betteti et al.
Firing rate models are dynamical systems widely used in applied and theoretical neuroscience to describe local cortical dynamics in neuronal populations. By providing a macroscopic perspective of neuronal activity, these models are essentia...
From Function to Implementation: Exploring Degeneracy in Evolved Artificial Agents [0.03%]
从功能到实现：探索人工代理中的退化现象
Zhimin Hu,Oğulcan Cingiler,Clifford Bohm et al.
Zhimin Hu et al.
Degeneracy-the ability of different structures to perform the same function-is a fundamental feature of biological systems, contributing to their robustness and evolvability. However, the ubiquity of degeneracy in systems generated through ...
Evren Gokcen,Anna I Jasper,Adam Kohn et al.
Evren Gokcen et al.
Gaussian processes are now commonly used in dimensionality-reduction approaches tailored to neuroscience, especially to describe changes in high-dimensional neural activity over time. As recording capabilities expand to include neuronal pop...
Toward Generalized Entropic Sparsification for Convolutional Neural Networks [0.03%]
面向卷积神经网络的通用熵化稀疏方法
Tin Barisin,Illia Horenko
Tin Barisin
Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem: if the network has $N$ neurons, then there are 2$^{N}$ possibilities to connect th...
Synergistic Pathways of Modulation Enable Robust Task Packing Within Neural Dynamics [0.03%]
协同调控机制使神经动力学中稳健的任务打包成为可能
Giacomo Vedovati,ShiNung Ching
Giacomo Vedovati
Understanding how brain networks learn and manage multiple tasks simultaneously is of interest in both neuroscience and artificial intelligence. In this regard, a recent research thread in theoretical neuroscience has focused on how recurre...