Domain Adaptation With Additional Features via Label-Aware and Graph-Based Fused Gromov-Wasserstein Optimal Transport [0.03%]
基于标签感知和图融合的Gromov-瓦瑟斯坦领域适应方法
Toshimitsu Aritake,Hideitsu Hino
Toshimitsu Aritake
In many domain adaptation tasks, the source and target domains share an identical feature space, so the domain gap arises only from the distributional shift. In practice; however, new-target-only features (e.g., sensors added after training...
Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment [0.03%]
基于微分同胚的矢量场对齐的动力学模型比较方法研究
Ruiqi Chen,Giacomo Vedovati,Todd Braver et al.
Ruiqi Chen et al.
Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience as a vehicle for hypothesis generation and data analysis. Evaluating the dynamics in such models is key to understanding ...
Global Stability of a Hebbian/Anti-Hebbian Network for Principal Subspace Learning [0.03%]
具主子空间学习的赫布/反赫布网络的全局稳定性分析
David Lipshutz,Robert J Lipshutz
David Lipshutz
Biological neural networks self-organize according to local synaptic modifications to produce stable computations. How modifications at the synaptic level give rise to such computations at the network level remains an open question. Pehleva...
Takuma Sumi,Georgi S Medvedev
Takuma Sumi
Graph signal processing (GSP) extends classical signal processing to signals defined on graphs, enabling filtering, spectral analysis, and sampling of data generated by networks of various kinds. Graphon signal processing (GnSP) develops th...
Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann's [0.03%]
类似冯·诺依曼的高维计算架构的自主学习方法
Pentti Kanerva
Pentti Kanerva
We model human and animal learning by computing with high-dimensional vectors (e.g., D = 10,000). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them in supe...
Infinite Horizon Control With Nonlinear Dynamics Models Reproduces Temporal Modulation of Reaching Movements [0.03%]
基于非线性动力学模型的无限时域控制重现了抓取运动中的时间调制现象
Antoine De Comite,Hari Teja Kalidindi,J Andrew Pruszynski et al.
Antoine De Comite et al.
Movement duration, a fundamental aspect of motor control, is often viewed as a preprogrammed parameter requiring dedicated selection mechanisms. An alternative view posits that movement duration emerges from the control policy itself. Here,...
Toward Enhancing RMSProp With Forward-Looking Gradient Updates for Complex Loss Landscapes [0.03%]
适用于复杂损失分布的前视梯度更新增强RMSProp算法研究
Rafał Wolniak,Bożena Kostek
Rafał Wolniak
This letter introduces a novel algorithm for training deep neural networks with many nonlinear layers. Our method uses an approximated integrated gradient that is averaged over the range of the weight update to more accurately capture the l...
Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales [0.03%]
类似匹配网络：赫布学习和多时间尺度收敛性
Veronica Centorrino,Francesco Bullo,Giovanni Russo
Veronica Centorrino
A recent breakthrough in biologically plausible normative frameworks for dimensionality reduction is based on the similarity matching cost function and the low-rank matrix approximation problem. Despite clear biological interpretation, succ...
William H Alexander
William H Alexander
To explain behavioral effects, models of cognitive control frequently rely on task information that the modeler provides. Hard-wired information can include labeling task dimensions as being relevant or irrelevant, defining which task stimu...
Thousand Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference [0.03%]
千大脑系统：快速而稳健学习和推理的感运动智能
Niels Leadholm,Viviane Clay,Scott Knudstrup et al.
Niels Leadholm et al.
Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in sensorimotor interactions, and structured knowledge ...