Périphérique d'entrée

Résumé

Un périphérique d'entrée est un équipement informatique périphérique permettant de fournir des données à un système de traitement de l'information tel qu'un ordinateur. vignette|Un clavier d'ordinateur, périphérique d'entrée pour transmettre de l'information en pressant des touches En informatique, les logiciels ont souvent besoin d'entrée fournies par l'utilisateur. Afin de permettre à ce dernier d'interagir avec l'ordinateur, différents types de dispositifs électroniques ont été développés au cours du temps, avec plus ou moins de succès. Types d'entrée - données Les différents périphériques peuvent commodément être classés sur la base du type d'information qu'ils peuvent fournir. ** flottant ** booléen

Types composites ** listes de types simples ** structures de types simples ou composites

En général, les périphériques d'entrée fournissent des données composites. Plus de détails seront donnés plus loin dans cet article. Nature des données Action

Source officielle

https://fr.wikipedia.org/wiki/P%C3%A9riph%C3%A9rique_d'entr%C3%A9e

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (100)

Chargement

Afficher plus

Publications associées

Chargement

Personnes associées (34)

Personnes associées

Chargement

Unités associées (21)

Unités associées

Chargement

Concepts associés (28)

Concepts associés

Chargement

Cours associés (58)

Cours associés

Chargement

Séances de cours associées (158)

Séances de cours associées

Chargement

Publications associées (100)

Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning

Hakgu Kim

Our work addresses long-term motion context issues for predicting future frames. To predict the future precisely, it is required to capture which long-term motion context (e.g., walking or running) the input motion (e.g., leg movement) belongs to. The bottlenecks arising when dealing with the long-term motion context are: (i) how to predict the long-term motion context naturally matching input sequences with limited dynamics, (ii) how to predict the long-term motion context with high-dimensionality (e.g., complex motion). To address the issues, we propose novel motion context-aware video prediction. To solve the bottleneck (i), we introduce a long-term motion context memory (LMC-Memory) with memory alignment learning. The proposed memory alignment learning enables to store long-term motion contexts into the memory and to match them with sequences including limited dynamics. As a result, the long-term context can be recalled from the limited input sequence. In addition, to resolve the bottleneck (ii), we propose memory query decomposition to store local motion context (i.e., low-dimensional dynamics) and recall the suitable local context for each local part of the input individually. It enables to boost the alignment effects of the memory. Experimental results show that the proposed method outperforms other sophisticated RNN-based methods, especially in long-term condition. Further, we validate the effectiveness of the proposed network designs by conducting ablation studies and memory feature analysis. The source code of this work is available(dagger).

IEEE COMPUTER SOC2021

Chargement

Poly-NL: Linear Complexity Non-local Layers With 3rd Order Polynomials

Grigorios Chrysos, Filippos Kokkinos

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the effectiveness of non-local layers, but also determine a complexity that scales quadratically with respect to the input size both in space and time. This is a severely limiting factor that practically hinders the applicability of non-local blocks to even moderately sized inputs. Previous works focused on reducing the complexity by modifying the underlying matrix operations, however in this work we aim to retain full expressiveness of non-local layers while keeping complexity linear. We overcome the efficiency limitation of non-local blocks by framing them as special cases of 3rd order polynomial functions. This fact enables us to formulate novel fast Non-Local blocks, capable of reducing the complexity from quadratic to linear with no loss in performance, by replacing any direct computation of pairwise similarities with element-wise multiplications. The proposed method, which we dub as "Poly-NL", is competitive with state-of-the-art performance across image recognition, instance segmentation, and face detection tasks, while having considerably less computational overhead.

IEEE2021

Chargement

At the LENI a heat pump model has been developed, which aims to simulate a single state compression heat pump in both steady state and transient regime. For gaining the experimental data and for the simulation the same set of input data is used. The goal is to approximate the output values of the model ym to the ones measured in the experiments. Therefore a certain number of parameters need to be defined in order of obtaining the highest accuracy possible. At the beginning these different parameters γ need to be found and a criterion needs to be appointed which can be used to judge the accuracy of the model. The first approach to the identification is to only work with the steady states. This includes to select steady values out of a data sheet and to change the model so that only steady states are computed. As soon as the model is successfully running for the steady states an optimizer needs to be chosen to finally output the best values of parameters. Subsequently the improvement of the output vector ym needs to be checked. As during the examination some computational problems have been revealed, which interfered with the optimization, various influences on the heat pump model were investigated. It was tried to find the reason for numerical problems and to eliminate those in order to finally be able to optimise the parameters. To identify the model in the transient regime the model needs to be linearised at a typical operation condition. The new chosen criterion must also take into account the transient regimes and the optimality of the solution has to be proved. The numerical problems which exist for the steady state also influence the transient regime. As the emphasis was therefore put on finding the origin of the instabilities, the identification of the transient regime was only briefly worked on.

2010

Chargement

Afficher plus