• Aucun résultat trouvé

Deep convolutional neural networks

Learning to recognise 3D human action from a new skeleton-based representation using deep convolutional neural networks

Learning to recognise 3D human action from a new skeleton-based representation using deep convolutional neural networks

... Residual Networks (Inception-ResNets) [ 91 ] or Densely Connected Convolutional Networks (DenseNet [ 92 ...as deep learning based approaches [ 93 , 94 ], KWE and KCE methods [ 10 ...very ...

12

Classification of Time-Series Images Using Deep Convolutional Neural Networks

Classification of Time-Series Images Using Deep Convolutional Neural Networks

... ABSTRACT Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw ...the deep CNN ...

9

Energy Efficient Techniques using FFT for Deep Convolutional Neural Networks

Energy Efficient Techniques using FFT for Deep Convolutional Neural Networks

... INTRODUCTION Deep convolutional neural networks (CNNs) [1], [2] have achieved tremendous successes in a wide range of machine learning applications, including image recognition, computer ...

7

Classification of Time-Series Images Using Deep Convolutional Neural Networks

Classification of Time-Series Images Using Deep Convolutional Neural Networks

... 2-stage deep CNN model is applied here with 1-channel input of size 28 × 28 and the output layer with c ...The convolutional layer is the core building block of a CNN and exploits spatially local ...

9

Detection of Cardiac Arrhythmias From Varied Length Multichannel Electrocardiogram Recordings Using Deep Convolutional Neural Networks

Detection of Cardiac Arrhythmias From Varied Length Multichannel Electrocardiogram Recordings Using Deep Convolutional Neural Networks

... Using Deep Convolutional Neural Networks Marwen Sallem 1 , Amina Ghrissi 2 , Adnen Saadaoui 3 and Vicente Zarzoso 2 1 National Institute of Applied Sciences and Technology, MMA Laboratory, ...

5

Learning Sparse Filters In Deep Convolutional Neural Networks With A l 1 /l 2 Pseudo-Norm

Learning Sparse Filters In Deep Convolutional Neural Networks With A l 1 /l 2 Pseudo-Norm

... In this paper, we present a sparsity-inducing regularization term based on the ratio l 1 /l 2 pseudo-norm defined on the filter coefficients. By defin- ing this pseudo-norm appropriately for the different filter kernels, ...

16

2020 — Modeling information flow through deep convolutional neural networks

2020 — Modeling information flow through deep convolutional neural networks

... using convolutional neural ...the deep convolutional neural network structure as a Markov process, where the filter output is represented as random variable 𝑌 defined by a probability ...

180

Deep convolutional neural networks to monitor coralligenous reefs: Operationalizing biodiversity and ecological assessment

Deep convolutional neural networks to monitor coralligenous reefs: Operationalizing biodiversity and ecological assessment

... Abstract Monitoring the ecological status of natural habitats is crucial to the conservation process, as it enables the implementation of efficient conservation policies. Nowadays, it is increasingly possible to automate ...

33

Are Topographic Deep Convolutional Neural Networks Better Models of the Ventral Visual Stream?

Are Topographic Deep Convolutional Neural Networks Better Models of the Ventral Visual Stream?

... - deep artificial neural networks (ANNs) – have “IT” layers that lack ...Topographic Deep ANNs (TDANNs) by incorporating a proxy wiring cost alongside the standard ImageNet categorization cost ...

5

Predicting the Propagation of Acoustic Waves using Deep Convolutional Neural Networks

Predicting the Propagation of Acoustic Waves using Deep Convolutional Neural Networks

... both networks, where initial conditions correspond to the analytical solution for the one-dimensional propagation of a Gaussian pulse, propagating on both directions along the ...the networks were trained ...

19

Deep Background Subtraction with Scene-Specific Convolutional Neural Networks

Deep Background Subtraction with Scene-Specific Convolutional Neural Networks

... Abstract—Background subtraction is usually based on low- level or hand-crafted features such as raw color components, gradients, or local binary patterns. As an improvement, we present a background subtraction algorithm ...

5

Relating images and 3D models with convolutional neural networks

Relating images and 3D models with convolutional neural networks

... This is a very generic problem which can be approached in several ways. In this thesis, we focus on exploring the representational power of Deep Convolutional Neural Networks (CNNs) to achieve ...

136

Convolutional neural networks for atomistic systems

Convolutional neural networks for atomistic systems

... (convolutional neural networks for atom- istic systems), for calculating the total energy of atomic systems which rivals the com- putational cost of empirical potentials while maintaining the ...

23

Robust parallel-gripper grasp getection using convolutional neural networks

Robust parallel-gripper grasp getection using convolutional neural networks

... To perform autonomous grasping, the first step is to take a sensory input, such as an image, and produce a grasp configuration. The arrival of active 3D cameras, like the Microsoft Kinect, enriched the sensing ...

84

Spatio-temporal convolutional neural networks for failure prediction

Spatio-temporal convolutional neural networks for failure prediction

... Next, our architecture is based on deep residual lear- ning. Roughly speaking, a bloc of convolution and poo- ling layers in the classical CNN presented in paragraph 1.2.2 learns directly an intermediate function ...

5

Lip Reading with Hahn Convolutional Neural Networks moments

Lip Reading with Hahn Convolutional Neural Networks moments

... on Deep bottleneck features extraction directly from pixels was introduced by Petridis and Pantic, 2016 [7], where the authors trained a model using Long-Short Term Memory (LSTM), this method achieved ...

28

Comparing learned representations of deep neural networks

Comparing learned representations of deep neural networks

... of deep neural network architectures have obtained substan- tial accuracy improvements in tasks such as image classification, speech recognition, and machine translation, yet little is known about how ...

64

Automated atrial fibrillation source detection using shallow convolutional neural networks

Automated atrial fibrillation source detection using shallow convolutional neural networks

... Recently, deep learning architectures like convolutional neural networks (CNNs) have gained attention mainly by their power of automat- ically extracting complex features from signals and ...

5

High-Resolution Semantic Labeling with Convolutional Neural Networks

High-Resolution Semantic Labeling with Convolutional Neural Networks

... use deep multi-layer schemes with down- sampling because we actually consider that certain objects can only be detected at the upper layers of the network, when a large amount of context has been taken into ...

14

Learning Activation Functions in Deep Neural Networks

Learning Activation Functions in Deep Neural Networks

... 2. Convolutional Neural Networks ...layer networks like Hebb (Hebb, 1949), ADALINE (Widrow et Hoff, 1960) and Perceptrons (Rosenblatt, ...

171

Show all 5592 documents...

Sujets connexes