CNN | EPFL Graph Search

Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Découvrez-en plus sur les applications Graph.

Cable News Network (CNN) est une chaîne de télévision d'information en continu américaine fondée en 1980 par Ted Turner. La société est rachetée en 1996 par WarnerMedia. La chaîne est connue pour sa couverture en direct dramatique (et parfois sensationnaliste) de breaking news, ou édition spéciale en français, qui peut durer des jours voire des semaines. Son audience est principalement progressiste. Description Elle appartient à une entité commerciale dénommée CNN News Group, qui se compose de plusieurs chaînes incluant CNN/U.S. et CNN en Español pour les États-Unis, CNN International, ainsi que CNN Türk et CNNj. CNN International est disponible dans le monde entier. La petite sœur de CNN/U.S. est le leader de l'information et une ressource indispensable pour toutes les rédactions de la planète. Historique Lancement et expansion vignette|droite|Le CNN Center à Atlanta. vignette|La newsroom de la chaîne. vignette|Vue aérienne du siège d'Atlanta. vign

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 (35)

Chargement

Afficher plus

Publications associées

Chargement

Personnes associées (8)

Personnes associées

Chargement

Unités associées (6)

Unités associées

Chargement

Concepts associés (82)

Concepts associés

Chargement

Cours associés (11)

Cours associés

Chargement

Séances de cours associées (16)

Afficher plus

Séances de cours associées

Chargement

Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

Pascal Fua, David Honzátko, Engin Türetken

The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task particularly difficult for non-convex real-world surfaces. State-of-the-art methods for calibrated photometric stereo address these issues using convolutional neural networks (CNNs) that primarily aim to capture either the spatial context among adjacent pixels or the photometric one formed by illuminating a sample from adjacent directions. In this paper, we bridge these two objectives and introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. In contrast to existing approaches that rely on standard 2D CNNs and regress directly to surface normals, we argue that using separable 4D convolutions and regressing to 2D Gaussian heat-maps severely reduces the size of the network and leads to more stable predictions. Our experimental results on a real-world photometric stereo benchmark show that the proposed approach outperforms the existing published methods in accuracy. The source code for our method is available at https://github.com/DawyD/UNet-PS-4D.

IEEE COMPUTER SOC2021

Chargement

An Accelerator for High Efficient Vision Processing

Zidong Du, Robert Fasthuber, Qi Guo, Paolo Ienne

In recent years, neural network accelerators have been shown to achieve both high energy efficiency and high performance for a broad application scope within the important category of recognition and mining applications. Still, both the energy efficiency and performance of such accelerators remain limited by memory accesses. In this paper, we focus on image applications, arguably the most important category among recognition and mining applications. The neural networks which are state-of-the-art for these applications are convolutional neural networks (CNNs), and they have an important property: weights are shared among many neurons, considerably reducing the neural network memory footprint. This property allows to entirely map a CNN within an SRAM, eliminating all DRAM accesses for weights. By further hoisting this accelerator next to the image sensor, it is possible to eliminate all remaining DRAM accesses, i.e., for inputs and outputs. In this paper, we propose such a CNN accelerator, placed next to a CMOS or CCD sensor. The absence of DRAM accesses combined with a careful exploitation of the specific data access patterns within CNNs allows us to design an accelerator which is highly energy-efficient. We present a single-core implementation down to the layout at 65 nm, with a modest footprint of 5.94mm(2) and consuming only 336mm(2), but still about 30x faster than high-end GPUs. For visual processing with higher resolution and frame-rate requirements, we further present a multicore implementation with elevated performance.

Ieee-Inst Electrical Electronics Engineers Inc2017

Chargement

Running Efficiently CNNs on the Edge Thanks to Hybrid SRAM-RRAM In-Memory Computing

Giovanni Ansaloni, David Atienza Alonso, Alexandre Sébastien Julien Levisse, Flavio Ponzina, Marco Antonio Rios

The increasing size of Convolutional Neural Networks (CNNs) and the high computational workload required for inference pose major challenges for their deployment on resource-constrained edge devices. In this paper, we address them by proposing a novel In-Memory Computing (IMC) architecture. Our IMC strategy allows us to efficiently perform arithmetic operations based on bitline computing, enabling a high degree of parallelism while reducing energy-costly data transfers. Moreover, it features a hybrid memory structure, where a portion of each subarray, dedicated to storing CNN weights, is implemented as high-density, zero-standby-power Resistive RAM. Finally, it exploits an innovative method for storing quantized weights based on their value, named Weight Data Mapping (WDM), which further increases efficiency. Compared to state-of-the-art IMC alternatives, our solution provides up to 93% improvements in energy efficiency and up to 6x less run-time when performing inference on Mobilenet and AlexNet neural networks.

2021

Chargement

Afficher plus

The New York Times

The New York Times (prononcé en anglais : ), abrégé NYT est un quotidien new-yorkais fondé en 1851, publié en anglais, espagnol, et chinois. Il est parfois surnommé The Grey Lady. Le New York Times

New York

New York (prononcé en anglais : ), officiellement nommée en, connue également sous les noms et abréviations de en ou en (pour éviter la confusion avec l'État de New York), et dont le surnom le plus co

YouTube

YouTube (en français : ou , en anglais américain : , en anglais standard , en anglais australien ) est un site web d'hébergement de vidéos et média social sur lequel les utilisateurs peuvent envoyer,

CS-233(a): Introduction to machine learning (BA3)

Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.

CS-503: Visual intelligence : machines and minds

The course will discuss classic material as well as recent advances in computer vision and machine learning relevant to processing visual data with a primary focus on embodied intelligence and vision for active agents.

EE-608: Deep Learning For Natural Language Processing

The Deep Learning for NLP course provides an overview of neural network based methods applied to text. The focus is on models particularly suited to the properties of human language, such as categorical, unbounded, and structured representations, and very large input and output vocabularies.