Buscador de Tesis y publicaciones académicas

NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognition

Kanglei Zhou · Ruizhi Cai · Hubert P.H. Shum · Frederick W.B. Li · y 1 más

Skeleton-based action recognition aims to recognize human actions from sequences of human joint coordinates. Most existing Spatial-Temporal Graph Convolutional Networks (STGCNs) have achieved promising results by modeling skeletal structures with implicit spatial-temporal representations. However, our empirical study r...

Non-data-splitting estimator selection for regression in exponential families

Juntong Chen

We observe $n$ independent pairs of random variables $(W_{i}, Y_{i})$, where the conditional distribution of $Y_{i}$ given $W_{i}=w_{i}$ follows a one-parameter exponential family with parameter $\bsg^{*}(w_{i})\in\R$. Our goal is to estimate the regression function $\bsg^{*}$. We start with an arbitrary collection of...

Threefolds containing all curves are rationally connected

Sixuan Lou

Any smooth projective curve embeds into $\mathbb{P}^3$. More generally, any curve embeds into a rationally connected variety of dimension at least three. We prove conversely that if every curve embeds in a variety $X$, then $X$ contains a rationally connected subvariety of dimension at least three. In particular, "all...

Integrating Gaussian random functions with genetic algorithms for the optimization of functionally graded lattice structures

Agrawal, Piyush · Agrawal, Manish

The properties of lattice-based structures can be enhanced by varying their geometric parameters in a graded manner, and the gradation can be tailored to extremize a particular objective. In this manuscript, we propose a non-gradient-based optimization framework to find the tailor-made graded profiles for lattice-based...

Black-box PWPP is not Turing-closed

Pavel Hubáček

We establish that adaptive collision-finding queries are strictly more powerful than non-adaptive ones by proving that the complexity class PWPP (Polynomial Weak Pigeonhole Principle) is not closed under adaptive Turing reductions in the black-box setting. Previously, PWPP was known to be closed under non-adaptive Turi...

Transfer of chloroplast rbcL and atpB genes to nucleus enables partial rescue of photoautotrophic growth of Chlamydomonas

Weida Shi · Mengyue Zhu · Chunhui Hou · Qiuling Fan · y 1 más

An ancient cyanobacterium has evolved through endosymbiosis to form extant chloroplasts of eukaryotic algae and higher plants. During this process, most genes have been transferred to the nuclear genomes. The chloroplast gene sets of different photosynthetic species are relatively conserved yet still exhibiting differe...

Interroger l’IA et Ilan : publier un livre pour catalyser la réaction

Dozo, Björn-Olav

Learning ‘to Studio’: The Role of Creative Pedagogy in Delivering Future Skills and How to Make It Happen

Ayliffe, Maggie · Bracey, Andrew · Lee, Joanne · Maier, Danica · y 1 más

An Approach for Specifying Reinforcement Learning Systems

Autoría no especificada

This repository contains the research artifacts produced as part of a master's dissertation proposal on the specification of systems incorporating Reinforcement Learning components.

Transmission of data from weighing stations for vehicles in motion using wireless sensor network devices

Mariusz Rychlicki · Zbigniew Kasprzyk · Tomasz Kamiński

The paper presents the general characteristics and design of weighing systems for vehicles in motion. A number of problems and limitations that accompany these systems on the way to achieving full automation of the weighing process at the desired level of accuracy are pointed out. The procedure and construction of pres...