Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Dahl, George E.; Yu, Dong; Deng, Li; Acero, Alex

doi:10.1109/tasl.2011.2134090

Cited by 2,670 publications

(1,244 citation statements)

References 61 publications

(67 reference statements)

Supporting

Mentioning

1,175

Contrasting

Unclassified

Order By: Relevance

“…State-ofthe-art performance has been reported in several domains, ranging from speech recognition [1], visual object recognition [2] to text processing [3]. In fact, it could be argued that the network's learning ability has been a crucial factor in the recent success of pattern recognition applications.…”

Section: Introductionmentioning

confidence: 99%

Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

et al. 2017

View full text Add to dashboard Cite

Abstract-Ship detection and classification is critical for national maritime security and national defense. Although some SAR (Synthetic Aperture Radar) image-based ship detection approaches have been proposed and used, they are not able to satisfy the requirement of real-world applications as the number of SAR sensors is limited, the resolution is low, and the revisit cycle is long. As massive optical remote sensing images of high resolution are available, ship detection and classification on theses images is becoming a promising technique, and has attracted great attention on applications including maritime security and traffic control. Some digital image processing methods have been proposed to detect ships in optical remote sensing images, but most of them face difficulty in terms of accuracy, performance and complexity. Recently, an autoencoder-based deep neural network with extreme learning machine was proposed, but it cannot meet the requirement of real-world applications as it only works with simple and small-scaled data sets. Therefore, in this paper, we propose a novel ship detection and classification approach which utilizes deep convolutional neural network (CNN) as the ship classifier. The performance of our proposed ship detection and classification approach was evaluated on a set of images downloaded from Google Earth at the resolution 0.5m. 99% detection accuracy and 95% classification accuracy were achieved. In model training, 75 speedup is achieved on 1 Nvidia Titanx GPU.

show abstract

Section: Introductionmentioning

confidence: 99%

Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Large-scale deep learning, for instance, Deep Neutral Network (DNN), has driven advances with higher accuracy than traditional techniques in many different fields especially at image classification [1,2], speech recognition [3] and text processing [4]. To train DNNs on a large-scale, researchers have exploited distributed deep learning systems [1,5,6,7], such as DistBelief [1] and Tensorflow [7].…”

Section: Introductionmentioning

confidence: 99%

DLTAP: A Network-efficient Scheduling Method for Distributed Deep Learning Workload in Containerized Cluster Environment

Wang

Liu

2017

ITM Web Conf.

View full text Add to dashboard Cite

Abstract:Deep neural networks (DNNs) have recently yielded strong results on a range of applications. Training these DNNs using a cluster of commodity machines is a promising approach since training is time consuming and compute-intensive. Furthermore, putting DNN tasks into containers of clusters would enable broader and easier deployment of DNN-based algorithms. Toward this end, this paper addresses the problem of scheduling DNN tasks in the containerized cluster environment. Efficiently scheduling data-parallel computation jobs like DNN over containerized clusters is critical for job performance, system throughput, and resource utilization. It becomes even more challenging with the complex workloads. We propose a scheduling method called Deep Learning Task Allocation Priority (DLTAP) which performs scheduling decisions in a distributed manner, and each of scheduling decisions takes aggregation degree of parameter sever task and worker task into account, in particularly, to reduce cross-node network transmission traffic and, correspondingly, decrease the DNN training time. We evaluate the DLTAP scheduling method using a state-of-the-art distributed DNN training framework on 3 benchmarks. The results show that the proposed method can averagely reduce 12% cross-node network traffic, and decrease the DNN training time even with the cluster of low-end servers.

show abstract

“…Recently deep learning-based methods have demonstrated excellent performance on different artificial-intelligence tasks, including speech recognition (Hinton et al, 2012a), natural language processing (Dahl et al, 2012), and computer vision (Krizhevsky et al, 2012). In the later area, Convolutional Neural Networks (CNNs) play a major role for processing visual-related problems such as image classification (Lee et al, 2009;Sermanet et al, 2013), object detection , and face recognition (Taigman et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Deep learning for superpixel-based classification of remote sensing images

Gonzalo-Martín

García‐Pedrero

Lillo‐Saavedra

et al. 2016

GEOBIA 2016: Solutions and Synergies

View full text Add to dashboard Cite

ABSTRACT:Recently deep learning-based methods have demonstrated excellent performance on different artificial-intelligence tasks. Even though, in the last years, several related works are found in the literature in the remote sensing field, a small percentage of them address the classification problem. These works propose schemes based on image patches to perform pixel-based image classification. Due to the typical remote sensing image size, the main drawback of these schemes is the time required by the window-sliding process implied in them. In this work, we propose a strategy to reduce the time spent on the classification of a new image through the use of superpixel segmentation. Several experiments using CNNs trained with different sizes of patches and superpixels have been performed on the ISPRS semantic labeling benchmark. Obtained results show that while the accuracy of the classification carried out by using superpixels is similar to the results generated by pixel-based approach, the expended time is dramatically decreased by means of reducing the number of elements to label.

show abstract

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Cited by 2,670 publications

References 61 publications

Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

DLTAP: A Network-efficient Scheduling Method for Distributed Deep Learning Workload in Containerized Cluster Environment

Deep learning for superpixel-based classification of remote sensing images

Contact Info

Product

Resources

About