Puyu Wang,Yunwen Lei,Di Wang et al.
Puyu Wang et al.
Significant progress has been made recently in understanding the generalization of neural networks (NNs) trained by gradient descent (GD) using the algorithmic stability approach. However, most of the existing research has focused on one-hi...
Christopher J Kymn,Denis Kleyko,E Paxon Frady et al.
Christopher J Kymn et al.
We introduce residue hyperdimensional computing, a computing framework that unifies residue number systems with an algebra defined over random, high-dimensional vectors. We show how residue numbers can be represented as high-dimensional vec...
Peilin Liu,Ding-Xuan Zho
Peilin Liu
In recent years, models based on the transformer architecture have seen widespread applications and have become one of the core tools in the field of deep learning. Numerous successful and efficient techniques, such as parameter-efficient f...
Selective Inference for Change Point Detection by Recurrent Neural Network [0.03%]
基于循环神经网络的变化点检测的择优推断
Tomohiro Shiraishi,Daiki Miwa,Vo Nguyen Le Duy et al.
Tomohiro Shiraishi et al.
In this study, we investigate the quantification of the statistical reliability of detected change points (CPs) in time series using a recurrent neural network (RNN). Thanks to its flexibility, RNN holds the potential to effectively identif...
Alex Heyman,Joel Zylberberg
Alex Heyman
Neural network pruning is a popular approach to reducing the computational costs of training and/or deploying a network and aims to do so while minimizing accuracy loss. Pruning methods that remove individual weights (fine granularity) can ...
Victor Geadah,Gabriel Barello,Daniel Greenidge et al.
Victor Geadah et al.
The sparse coding model posits that the visual system has evolved to efficiently code natural stimuli using a sparse set of features from an overcomplete dictionary. The original sparse coding model suffered from two key limitations; howeve...
Optimizing Attention and Cognitive Control Costs Using Temporally Layered Architectures [0.03%]
利用时间分层架构优化注意力和认知控制成本
Devdhar Patel,Terrence Sejnowski,Hava Siegelmann
Devdhar Patel
The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and ...
Zeyu Jing,Markus Meister
Zeyu Jing
Given a directed graph of nodes and edges connecting them, a common problem is to find the shortest path between any two nodes. Here we show that the shortest path distances can be found by a simple matrix inversion: if the edges are given ...
Relating Human Error-Based Learning to Modern Deep RL Algorithms [0.03%]
基于人类错误的学习与现代深度强化学习算法之间的关系研究
Michele Garibbo,Casimir J H Ludwig,Nathan F Lepora et al.
Michele Garibbo et al.
In human error-based learning, the size and direction of a scalar error (i.e., the "directed error") are used to update future actions. Modern deep reinforcement learning (RL) methods perform a similar operation but in terms of scalar rewar...
Gerrit Schmid,Sebastian Gottwald,Daniel A Braun
Gerrit Schmid
Complex information processing systems that are capable of a wide variety of tasks, such as the human brain, are composed of specialized units that collaborate and communicate with each other. An important property of such information proce...