Convolutional Neural Network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention both of industry and academia in the past few years. The existing reviews mainly focus on the applications of CNN in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide novel ideas and prospects in this fast-growing field as much as possible. Besides, not only two-dimensional convolution but also one-dimensional and multi-dimensional ones are involved. First, this review starts with a brief introduction to the history of CNN. Second, we provide an overview of CNN. Third, classic and advanced CNN models are introduced, especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for function selection. Fifth, the applications of one-dimensional, two-dimensional, and multi-dimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed to serve as guidelines for future work.

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN's applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work. 

/pdf/a-survey-of-convolutional-neural-networks-analysis-1hzyfrmo.pdf

Recent advances in convolutional neural network acceleration

This year's meeting is special First, it the first ACL meeting to be hosted jointly with our North-American chapter, the NAACL Second, it is also the ACL's 40th anniversary meeting: our association was created 13 June 1962, and its first meeting took place 25-26 August 1963 in DenverOur field has expanded quite a bit since then, and so have ACL meetings This year, our main conference program includes some 65 different refereed papers, covering most active research areas in computational linguistics And our extended program is complementing that with 19 system demonstrations, 4 tutorials, 12 Student Research papers, and no less than 11 different pre- and post-conference workshops presenting a total of about 150 papers

Proceedings of the 40th Annual Meeting on Association for Computational Linguistics

Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we called dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed.

Trainability of Dissipative Perceptron-Based Quantum Neural Networks

The success of traditional methods for solving computer vision problems heavily depends on the feature extraction process But Convolutional Neural Networks (CNN) have provided an alternative for automatically learning the domain specific features Now every problem in the broader domain of computer vision is re-examined from the perspective of this new methodology Therefore it is essential to figure-out the type of network specific to a problem In this work, we have done a thorough literature survey of Convolutional Neural Networks which is the widely used framework of deep learning With AlexNet as the base CNN model, we have reviewed all the variations emerged over time to suit various applications and a small discussion on the available frameworks for the implementation of the same We hope this piece of article will really serve as a guide for any neophyte in the area

A review on deep convolutional neural networks

Real-time sign language translation systems, that convert continuous sign sequences to text/speech, will facilitate communication between the deaf-mute community and the normal hearing majority. A translation system could be vision-based or sensor-based, depending on the type of input it receives. To date, most of the commercial systems for this purpose are sensor-based, which are expensive and not user-friendly. Vision-based sign translation systems are the need of the hour but should overcome many challenges to build a full-fledged working system. Preliminary investigations in this work have revealed that the traditional approaches to continuous sign language recognition (CSLR) using HMM, CRF and DTW, tried to solve the problem of Isolated Sign Language Recognition (ISLR) and extended the solution to CSLR, leading to reduced performance. The main challenge of identifying Movement Epenthesis (ME) segments in continuous utterances, were handled explicitly with these traditional methods. With the advent of technologies like Deep Learning, more feasible solutions for vision-based CSLR are emerging, which has led to an increase in the research on vision-based approaches. In this paper, a detailed review of all the works in vision-based CSLR is presented, based on the methods they have followed. The challenges posed in continuous sign recognition are also discussed in detail, followed by a brief on sensor-based systems and benchmark databases. Finally, performance evaluation of all the associated methods are performed, which leads to a short discussion on the overall study and concludes by pointing out future research directions in the field.

Understanding vision-based continuous sign language recognition

Recent advancements in machine translation tasks, with the advent of attention mechanisms and Transformer networks, have accelerated the research in Sign Language Translation (SLT), a spatio-temporal vision translation task. Fundamentally, Transformers are unaware of the sequential orderings in input, and therefore position-information should be explicitly fed into them. The sequence learning capability of Transformers is heavily dependent on this ordering information. Compared to the existing Transformer models for SLT that use baseline version with sinusoidal position embedding, this work focuses on incorporating a new positioning scheme into the Transformer networks, in the context of SLT. This is the first work in SLT that explores the positioning scheme of Transformers for optimizing translation scores. The study proposes Gated Recurrent Unit (GRU)-Relative Sign Transformer (RST) for jointly learning Continuous Sign Language Recognition (CSLR) and translation. This model significantly improves the video translation quality. In this approach, GRU acts as the relative position encoder and RST is the Transformer model with relative position incorporated in the Multi-Head Attention (MHA). The evaluation was done on the RWTH-PHOENIX-2014T benchmark dataset. This study reports state-of-the-art Bilingual Evaluation Understudy (BLEU-4) score of 22.4 and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) score of 48.55 for SLT, with GRU-RST. The best Word Error Rate (WER) obtained with this approach is 23.5. A detailed study of the position encoding schemes of Transformers is presented. Further, we analyze the translation performance under various combinations of the positioning schemes.

/pdf/incorporating-relative-position-information-in-transformer-441p3j7qb3.pdf

Incorporating Relative Position Information in Transformer-Based Sign Language Recognition and Translation

A sign language translator is a utilitarian in facilitating communication between the deaf community and the hearing majority. This paper proffers an innovative specialized convolutional neural network (CNN) model, Sign-Net, to recognize hand gesture signs by incorporating scale-space theory to deep learning framework. The proposed model is an ensemble of CNNs—a low resolution network (LRN) and a high resolution network (HRN). This architecture of the proposed model allows the ensemble to work at different spatial resolutions and at varying depths of CNN. The Sign-Net model was assessed with static signs of American Sign Language—alphabets and digits. Since there exists no sign dataset for deep learning, the ensemble performance is evaluated on the synthetic dataset which we have collected for this task. Assessment of the synthetic dataset by Sign-Net reported an impressive accuracy of 74.5%, notably superior to the other existing models.

Neena Aloysius

Papers

A review on deep convolutional neural networks

Understanding vision-based continuous sign language recognition

Incorporating Relative Position Information in Transformer-Based Sign Language Recognition and Translation

An Ensembled Scale-Space Model of Deep Convolutional Neural Networks for Sign Language Recognition