scholarly journals Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 444
Author(s):  
Zhao Yang ◽  
Shengbing Zhang ◽  
Ruxu Li ◽  
Chuxi Li ◽  
Miao Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Structure ◽  
High Accuracy ◽  
Search Direction ◽  
Search Process ◽  
Search Efficiency ◽  
Neural Architecture ◽  
Efficient Resource ◽  
Resource Aware

With the development of deep learning technologies and edge computing, the combination of them can make artificial intelligence ubiquitous. Due to the constrained computation resources of the edge device, the research in the field of on-device deep learning not only focuses on the model accuracy but also on the model efficiency, for example, inference latency. There are many attempts to optimize the existing deep learning models for the purpose of deploying them on the edge devices that meet specific application requirements while maintaining high accuracy. Such work not only requires professional knowledge but also needs a lot of experiments, which limits the customization of neural networks for varied devices and application scenarios. In order to reduce the human intervention in designing and optimizing the neural network structure, multi-objective neural architecture search methods that can automatically search for neural networks featured with high accuracy and can satisfy certain hardware performance requirements are proposed. However, the current methods commonly set accuracy and inference latency as the performance indicator during the search process, and sample numerous network structures to obtain the required neural network. Lacking regulation to the search direction with the search objectives will generate a large number of useless networks during the search process, which influences the search efficiency to a great extent. Therefore, in this paper, an efficient resource-aware search method is proposed. Firstly, the network inference consumption profiling model for any specific device is established, and it can help us directly obtain the resource consumption of each operation in the network structure and the inference latency of the entire sampled network. Next, on the basis of the Bayesian search, a resource-aware Pareto Bayesian search is proposed. Accuracy and inference latency are set as the constraints to regulate the search direction. With a clearer search direction, the overall search efficiency will be improved. Furthermore, cell-based structure and lightweight operation are applied to optimize the search space for further enhancing the search efficiency. The experimental results demonstrate that with our method, the inference latency of the searched network structure reduced 94.71% without scarifying the accuracy. At the same time, the search efficiency increased by 18.18%.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

scholarly journals Learners Demographics Classification on MOOCs During the COVID-19: Author Profiling via Deep Learning Based on Semantic and Syntactic Representations

2021 ◽  
Vol 6 ◽  
Author(s):  
Tahani Aljohani ◽  
Alexandra I. Cristea
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Prediction Models ◽  
Short Term Memory ◽  
Methodological Approach ◽  
High Accuracy ◽  
Directional Model ◽  
Textual Representations ◽  
The One

Massive Open Online Courses (MOOCs) have become universal learning resources, and the COVID-19 pandemic is rendering these platforms even more necessary. In this paper, we seek to improve Learner Profiling (LP), i.e. estimating the demographic characteristics of learners in MOOC platforms. We have focused on examining models which show promise elsewhere, but were never examined in the LP area (deep learning models) based on effective textual representations. As LP characteristics, we predict here the employment status of learners. We compare sequential and parallel ensemble deep learning architectures based on Convolutional Neural Networks and Recurrent Neural Networks, obtaining an average high accuracy of 96.3% for our best method. Next, we predict the gender of learners based on syntactic knowledge from the text. We compare different tree-structured Long-Short-Term Memory models (as state-of-the-art candidates) and provide our novel version of a Bi-directional composition function for existing architectures. In addition, we evaluate 18 different combinations of word-level encoding and sentence-level encoding functions. Based on these results, we show that our Bi-directional model outperforms all other models and the highest accuracy result among our models is the one based on the combination of FeedForward Neural Network and the Stack-augmented Parser-Interpreter Neural Network (82.60% prediction accuracy). We argue that our prediction models recommended for both demographics characteristics examined in this study can achieve high accuracy. This is additionally also the first time a sound methodological approach toward improving accuracy for learner demographics classification on MOOCs was proposed.

scholarly journals Convolutional Neural Network for Iris Recognition

2021 ◽  
Author(s):  
Wael Alnahari
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Iris Recognition ◽  
Recognition System ◽  
High Accuracy ◽  
Accuracy Rate

Abstract In this paper, I proposed an iris recognition system by using deep learning via neural networks (CNN). Although CNN is used for machine learning, the recognition is achieved by building a non-trained CNN network with multiple layers. The main objective of the code the test pictures’ category (aka person name) with a high accuracy rate after having extracted enough features from training pictures of the same category which are obtained from a that I added to the code. I used IITD iris which included 10 iris pictures for 223 people.

scholarly journals Increasing of Thermal Images Resolution Using Deep Learning Neural Networks

2021 ◽  
Vol 25 (3) ◽  
pp. 31-35
Author(s):  
Piotr Więcek ◽  
Dominik Sankowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Execution Time ◽  
High Accuracy ◽  
New Method ◽  
Residual Network ◽  
Thermal Images ◽  
The Neural Network

The article presents a new algorithm for increasing the resolution of thermal images. For this purpose, the residual network was integrated with the Kernel-Sharing Atrous Convolution (KSAC) image sub-sampling module. A significant reduction in the algorithm’s complexity and shortening the execution time while maintaining high accuracy were achieved. The neural network has been implemented in the PyTorch environment. The results of the proposed new method of increasing the resolution of thermal images with sizes 32 × 24, 160 × 120 and 640 × 480 for scales up to 6 are presented.

scholarly journals MajraDoc an Image based Disease Detection App for Agricultural Plants using Deep Learning Techniques

2021 ◽  
Author(s):  
Sara Saleh Alfozan ◽  
Mohamad Mahdi Hassan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Food Safety ◽  
Early Detection ◽  
Deep Neural Network ◽  
High Accuracy ◽  
Vital Role ◽  
Mobile App ◽  
Learning Techniques ◽  
Agricultural Plants

Infection of agricultural plants is a serious threat to food safety. It can severely damage plants' yielding capacity. Farmers are the primary victims of this threat. Due to the advancement of AI, image-based intelligent apps can play a vital role in mitigating this threat by quick and early detection of plants infections. In this paper, we present a mobile app in this regard. We have developed MajraDoc to detect some common diseases in local agricultural plants. We have created a dataset of 10886 images for ten classes of plants diseases to train the deep neural network. The VGG-19 network model was modified and trained using transfer learning techniques. The model achieved high accuracy, and the application performed well in predicting all ten classes of infections.

scholarly journals Designing deep neural networks for continual learning in an open world

2021 ◽  
Author(s):  
◽  
Martin Mundt
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Network Architecture ◽  
Neural Network Training ◽  
Neural Network Architecture ◽  
Neural Architecture ◽  
Network Training ◽  
Classification Tasks ◽  
Continual Learning

Deep learning with neural networks seems to have largely replaced traditional design of computer vision systems. Automated methods to learn a plethora of parameters are now used in favor of previously practiced selection of explicit mathematical operators for a specific task. The entailed promise is that practitioners no longer need to take care of every individual step, but rather focus on gathering big amounts of data for neural network training. As a consequence, both a shift in mindset towards a focus on big datasets, as well as a wave of conceivable applications based exclusively on deep learning can be observed. This PhD dissertation aims to uncover some of the only implicitly mentioned or overlooked deep learning aspects, highlight unmentioned assumptions, and finally introduce methods to address respective immediate weaknesses. In the author’s humble opinion, these prevalent shortcomings can be tied to the fact that the involved steps in the machine learning workflow are frequently decoupled. Success is predominantly measured based on accuracy measures designed for evaluation with static benchmark test sets. Individual machine learning workflow components are assessed in isolation with respect to available data, choice of neural network architecture, and a particular learning algorithm, rather than viewing the machine learning system as a whole in context of a particular application. Correspondingly, in this dissertation, three key challenges have been identified: 1. Choice and flexibility of a neural network architecture. 2. Identification and rejection of unseen unknown data to avoid false predictions. 3. Continual learning without forgetting of already learned information. These latter challenges have already been crucial topics in older literature, alas, seem to require a renaissance in modern deep learning literature. Initially, it may appear that they pose independent research questions, however, the thesis posits that the aspects are intertwined and require a joint perspective in machine learning based systems. In summary, the essential question is thus how to pick a suitable neural network architecture for a specific task, how to recognize which data inputs belong to this context, which ones originate from potential other tasks, and ultimately how to continuously include such identified novel data in neural network training over time without overwriting existing knowledge. Thus, the central emphasis of this dissertation is to build on top of existing deep learning strengths, yet also acknowledge mentioned weaknesses, in an effort to establish a deeper understanding of interdependencies and synergies towards the development of unified solution mechanisms. For this purpose, the main portion of the thesis is in cumulative form. The respective publications can be grouped according to the three challenges outlined above. Correspondingly, chapter 1 is focused on choice and extendability of neural network architectures, analyzed in context of popular image classification tasks. An algorithm to automatically determine neural network layer width is introduced and is first contrasted with static architectures found in the literature. The importance of neural architecture design is then further showcased on a real-world application of defect detection in concrete bridges. Chapter 2 is comprised of the complementary ensuing questions of how to identify unknown concepts and subsequently incorporate them into continual learning. A joint central mechanism to distinguish unseen concepts from what is known in classification tasks, while enabling consecutive training without forgetting or revisiting older classes, is proposed. Once more, the role of the chosen neural network architecture is quantitatively reassessed. Finally, chapter 3 culminates in an overarching view, where developed parts are connected. Here, an extensive survey further serves the purpose to embed the gained insights in the broader literature landscape and emphasizes the importance of a common frame of thought. The ultimately presented approach thus reflects the overall thesis’ contribution to advance neural network based machine learning towards a unified solution that ties together choice of neural architecture with the ability to learn continually and the capability to automatically separate known from unknown data.

Genetic Programming for Letters Identification Based on Neural Network

2015 ◽  
Vol 734 ◽  
pp. 642-645
Author(s):  
Yan Hui Liu ◽  
Zhi Peng Wang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Genetic Programming ◽  
Network Structure ◽  
High Accuracy ◽  
Identification System ◽  
Neural Network Structure ◽  
Hidden Layer

According to the problem that the letters identification is not high accuracy using neural networks, in this paper, an optimal neural network structure is designed based on genetic algorithm to optimize the number of hidden layer. The English letters can be identified by optimal neural network. The results obtained in the genetic programming optimizations are very satisfactory. Experiments show that the identification system has higher accuracy and achieved good ideal letters identification effect.

scholarly journals AMBIENT: Accelerated Convolutional Neural Network Architecture Search for Regulatory Genomics

2021 ◽  
Author(s):  
Zijun Zhang ◽  
Evan M. Cofer ◽  
Olga G. Troyanskaya
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Environmental Issue ◽  
Biological Sequences ◽  
Neural Network Architecture ◽  
Computing Power ◽  
Neural Architecture

Convolutional neural networks (CNN) have become a standard approach for modeling genomic sequences. CNNs can be effectively built by Neural Architecture Search (NAS) by trading computing power for accurate neural architectures. Yet, the consumption of immense computing power is a major practical, financial, and environmental issue for deep learning. Here, we present a novel NAS framework, AMBIENT, that generates highly accurate CNN architectures for biological sequences of diverse functions, while substantially reducing the computing cost of conventional NAS.

scholarly journals A Review of Automatic Music Generation Based on Performance RNN

2020 ◽  
Author(s):  
Jiyanbo Cao ◽  
Jinan Fiaidhi ◽  
Maolin Qi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Network Structure ◽  
Network Performance ◽  
State Of The Art ◽  
Learning Techniques ◽  
History Of ◽  
Music Generation ◽  
Automatic Music Generation

This paper has reviewed the deep learning techniques which used in music generation. The research was based on <i>Sageev Oore's</i> proposed LSTM based recurrent neural network (Performance RNN). We have study the history of automatic music generation, and now we are using a state of the art techniques to achieve this mission. We have conclude the process of making a MIDI file to a structure as input of Performance RNN and the network structure of it.

Sign in / Sign up

Export Citation Format

Share Document