scholarly journals Joint Channel Pruning and Quantization-Based CNN Network Learning with Mobile Computing-Based Image Recognition

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Huanyu Liu ◽  
Qing Luo ◽  
Mingmei Shao ◽  
Jeng-Shyang Pan ◽  
Junbao Li
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Rapid Development ◽  
Computational Cost ◽  
The Internet ◽  
New Era ◽  
Practical Applications ◽  
Model Compression ◽  
Smart Healthcare ◽  
Artificial Intelligence Technology

The development of the Internet and communication technology has ushered in a new era of the Internet of Things (IoT). Moreover, with the rapid development of artificial intelligence, objects are endowed with intelligence, such as home automation and smart healthcare, which are typical applications of artificial intelligence technology in IoT. With the rise of convolutional neural network (CNN) in the field of computer vision, more and more practical applications need to deploy CNN on mobile devices. However, due to the large amount of CNN computing operations and the large number of parameters, it is difficult to deploy on ordinary edge devices. The neural network model compression method has become a popular technology to reduce the computational cost and has attracted more and more attention. We specifically design a small target detection network for hardware platforms with limited computing resources, use pruning and quantization methods to compress, and demonstrate in VOC dataset and RSOD dataset on the actual hardware platform. Experiments show that the proposed method can maintain a fairly accurate rate while greatly speeding up the inference speed.

scholarly journals Artificial intelligence in artistic practices

2021 ◽  
pp. 41-50
Author(s):  
Asmati Chibalashvili
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Visual Arts ◽  
Human Condition ◽  
Human Intervention ◽  
Basic Principles ◽  
Generative Art ◽  
Works Of Art ◽  
Artificial Intelligence Technology ◽  
Emotionally Intelligent

The article considers methods of involving artificial intelligence in artistic practices. Based on the analysis of ways to use this technology in visual arts and music, the basic principles of working with artificial intelligence technology are identified, including: imitation of historical art, implemented in projects The Next Rembrandt and Choral; generative art, which is found in the works “Hyperbolic Composition І” and “Hyperbolic Composition ІІ” of S. Eaton and also in the AIVA program (Artificial Intelligence Virtual Artist). The importance of the mechanisms of neurobiology in the process of working with artificial intelligence on the example of the project “Neural Zoo” of S. Crespo, Iamus program, in which the development of musical material is based on the principle of evolution, is stated. In the application Endel and in the opera “Emotionally intelligent” Artificially Intelligent Brainwave Opera» of E. Perlman, a neural network is used to read information about the human condition and its further processing for modification into a sound landscape or image. The development of artificial intelligence and its use in artistic practices opens up new opportunities, expanding both the field of authors of artistic content and attracting new audience. This phenomenon provokes many issues, including: the ability to think artificially of artificial intelligence, the ability to create works of art without human intervention, as well as issues related to copyright.

scholarly journals Research On The Hybrid Teaching Method Of Ideological And Political Course Online And Offline In Higher Vocational Colleges Under The Background Of Internet

2021 ◽  
Vol 236 ◽  
pp. 05049
Author(s):  
Jihua Wen
Keyword(s):  
21St Century ◽  
Teaching Method ◽  
Rapid Development ◽  
The Internet ◽  
New Era ◽  
Teaching Content ◽  
Hybrid Teaching ◽  
Vocational Colleges ◽  
The Times ◽  
Theory System

In the 21st century, the rapid development of the Internet has affected all walks of life to varying degrees. In the era of rapid development of the Internet, the ideological and political teaching of higher vocational colleges lags behind the development of the times. Whether from the aspects of ideological and political teaching content, ideological and political teaching means or teaching teachers' accomplishment, how to better use the Internet to meet the teaching requirements of the new era is undoubtedly a major problem that higher vocational colleges need to think about in the teaching industry, so higher vocational colleges should seize the opportunity, face the difficulties and comply with the requirements of the new era, Construct the teaching theory system of ideological and political course with characteristic socialism.

Distant Teaching and Learning of BTIPS: Application in Pandemic Situation

2020 ◽  
Author(s):  
Zbigniew M. Bzymek
Keyword(s):  
Problem Solving ◽  
Engineering Design ◽  
Human Life ◽  
Rapid Development ◽  
Idea Generation ◽  
Teaching Experience ◽  
The Internet ◽  
Practical Applications ◽  
Main Challenge ◽  
New Situation

Abstract The world’s technology is developing very rapidly. To anticipate the course and results of such development is a task that is very crucial for the success of many technological undertakings and expansions. Engineering design is the branch of engineering that should predict the results of that rapid development. It should equip society with the tools for directing and controlling that development. It is a complex task that faces big challenges. The main challenge comes from society advancement and from the technology development itself. If the directing and controlling are done right the development would bring many benefits to humanity and would make human life easier and more comfortable. Doing it right however requires increased knowledge of the new features of technology and more skills in its application. In the difficult pandemic situation that knowledge and skills should be even greater because the outbreak of the disease creates additional traps and dangers. These conditions have to be taken under consideration and accepted as normal. The role of engineering design is to predict what harmful elements would be coming from both technological and social sources. The real goal however would be to exceed the expectations and not only neutralize them but change them from harmful into neutral, and then from neutral into friendly and helpful. Such actions follows recommendations of BTIPS (Brief Theory of Inventive Problem Solving) and is outlined in the BTIPS’s module “Prediction”. At the same time the developing civilization brings dangers for humans that were unknown before. These are bacterial and viruses’ attacks that limit personal relations between humans, requires new ways and new elements of communications, especially in internet contacts and in distant learning procedures. The contents of these components should be accurately predicted, well-orchestrated, well designed and precisely described. Recommendations for introducing BTIPS as a tool of engineering education in new situation should be carefully proposed and illustration examples, using new communication tools, should be developed. These should be applied in engineering theoretical courses and in practical applications during the senior design course of study and in industrial practice. This should be precise, clearly anticipating difficulties, pointing possible errors and ways of avoiding them. Teaching examples of problem solving and personal ways of communications between individual students, between groups of students, as well as between students and instructors should be further discussed. The examples of design ideas and problem solutions generated by students in design courses that were described in previous works of the author and his co-workers [1] should be related to pandemic situation. To define and formulate rules of teaching BTIPS in the pandemic situation is the necessity of our times. On every step of our lives we face the challenge of preventing harms and destruction that can be done by the contemporary surrounding world. The preventing actions can be designed by following rules of BTIPS and by apply approach recommended in its modules. The proposal of utilizing BTIPS application examples using the internet as a tool of expression is described in this paper. All of these are pointed out and some recommendations and examples are called. Adding description of corrections to the engineering curriculum is necessary in the new situation. It is an intention of the author to demonstrate a fragment of practical distant lecturing by internet during the IMECE 2020 internet sessions using the internet network and distant support from UConn computer Laboratory in Storrs, CT. Some example solutions of the idea generation are quoted in this paper. The comments coming from author’s teaching experience will be given during the presentation and practical advices for students and instructors will be passed to the audience. This paper is a companion to IMECE 2017-70438 [1]. Some original examples given in the paper 79418 are recommended for following and will be run by internet in pandemic situation of IMECE 2020.

Latest Technology and Future Trends

2021 ◽  
pp. 270-273
Author(s):  
Meghna Babubhai Patel ◽  
Jagruti N. Patel ◽  
Upasana M. Bhilota
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Smart Devices ◽  
The Internet ◽  
Future Trends ◽  
Internet Industry ◽  
The Neural Network ◽  
Dramatic Rise ◽  
Technological World ◽  
The Way

ANN can work the way the human brain works and can learn the way we learn. The neural network is this kind of technology that is not an algorithm; it is a network that has weights on it, and you can adjust the weights so that it learns. You teach it through trials. It is a fact that the neural network can operate and improve its performance after “teaching” it, but it needs to undergo some process of learning to acquire information and be familiar with them. Nowadays, the age of smart devices dominates the technological world, and no one can deny their great value and contributions to mankind. A dramatic rise in the platforms, tools, and applications based on machine learning and artificial intelligence has been seen. These technologies not only impacted software and the internet industry but also other verticals such as healthcare, legal, manufacturing, automobile, and agriculture. The chapter shows the importance of latest technology used in ANN and future trends in ANN.

scholarly journals Research Progress and Application of Computer Artificial Intelligence Technology

2018 ◽  
Vol 176 ◽  
pp. 01043 ◽  
Author(s):  
Jin Wei
Keyword(s):  
Artificial Intelligence ◽  
Rapid Development ◽  
Science And Technology ◽  
Development Trend ◽  
Concept Development ◽  
Research Progress ◽  
Huge Amount ◽  
Development History ◽  
Artificial Intelligence Technology ◽  
Major Application

With the development of science and technology, artificial intelligence technology has received more and more attention and attention. Under the background of the rapid development of big data and cloud computing, the artificial intelligence industry broke out. There is a huge amount of research on artificial intelligence and the artificial intelligence industry is huge. As far as the artificial intelligence industry in China is concerned, even the start is relatively late, but the industry scale, industrial layout, and technology research are all in a continuous improvement stage. Especially after the deepening of the layout of science and technology and manufacturing industries, the scale of artificial intelligence industry is further developed. More artificial intelligence products will appear at the same time. From the perspective of the concept, development history and new progress of artificial intelligence, this paper combines China’s artificial intelligence market and the development of artificial intelligence companies to analyze the current major application areas, and then further explore the future development trend of artificial intelligence.

Recent Advances in Medical Image Processing

2020 ◽  
pp. 1-14
Author(s):  
Zhen Huang ◽  
Qiang Li ◽  
Ju Lu ◽  
Junlin Feng ◽  
Jiajia Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Image Processing ◽  
Medical Imaging ◽  
Medical Image ◽  
Medical Image Processing ◽  
Convolution Neural Network ◽  
Artificial Intelligence Technology ◽  
Deep Convolution Neural Network

<b><i>Background:</i></b> Application and development of the artificial intelligence technology have generated a profound impact in the field of medical imaging. It helps medical personnel to make an early and more accurate diagnosis. Recently, the deep convolution neural network is emerging as a principal machine learning method in computer vision and has received significant attention in medical imaging. <b><i>Key Message:</i></b> In this paper, we will review recent advances in artificial intelligence, machine learning, and deep convolution neural network, focusing on their applications in medical image processing. To illustrate with a concrete example, we discuss in detail the architecture of a convolution neural network through visualization to help understand its internal working mechanism. <b><i>Summary:</i></b> This review discusses several open questions, current trends, and critical challenges faced by medical image processing and artificial intelligence technology.

scholarly journals A Study on the Design of Children Intelligent Guardianship Product Based on Artificial Intelligence Technology

2020 ◽  
Vol 179 ◽  
pp. 02050
Author(s):  
Yan-Xia Qu ◽  
Ming-Feng Wang
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Child Care ◽  
Design Process ◽  
Rapid Development ◽  
Parental Supervision ◽  
Parental Experience ◽  
Artificial Intelligence Technology ◽  
Intelligent Child ◽  
The Way

The rapid development of AI has affected the design process. The ability to analyze big data and AI’s efficiency, rapidity will bring great changes to the monitoring products especially for children. At present, the vast majority of intelligent child care products are based on the parental experience, designed in the aspect of parental supervision, and the children who use the product are often neglected. So change the way of designing, from the perspective of children using Intelligence technology, the ultimate child care products can play the most important role.

scholarly journals COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning

2019 ◽  
Author(s):  
Wenxiao Wang ◽  
Cong Fu ◽  
Jishun Guo ◽  
Deng Cai ◽  
Xiaofei He
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Computational Cost ◽  
Cross Layer ◽  
Optimal Solutions ◽  
Deep Convolutional Neural Networks ◽  
Model Compression ◽  
Deep Model ◽  
Network Compression ◽  
Novel Algorithm

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify layer-wise pruning ratios. 3) They are prone to generate sub-optimal solutions because they neglect the inequality between reducing parameters and reducing computational cost. Reducing the same number of parameters in different positions in the network may reduce different computational cost. To address the above problems, we develop a novel algorithm named as COP (correlation-based pruning), which can detect the redundant filters efficiently. We enable the cross-layer filter comparison through global normalization. We add parameter-quantity and computational-cost regularization terms to the importance, which enables the users to customize the compression according to their preference (smaller or faster). Extensive experiments have shown COP outperforms the others significantly. The code is released at https://github.com/ZJULearning/COP.

scholarly journals Application of Artificial Intelligence Technology Optimized by Deep Learning to Rural Financial Development and Rural Governance

2022 ◽  
Vol 30 (7) ◽  
pp. 1-23
Author(s):  
Hongwei Hou ◽  
Kunzhi Tang ◽  
Xiaoqian Liu ◽  
Yue Zhou
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Research Result ◽  
Customer Information ◽  
Rural Governance ◽  
Artificial Intelligence Technology ◽  
Reasonable Prediction

The aim of this article is to promote the development of rural finance and the further informatization of rural banks. Based on DL (deep learning) and artificial intelligence technology, data pre-processing and feature selection are conducted on the customer information of rural banks in a certain region, including the historical deposit and loan, transaction record, and credit information. Besides, four DL models are proposed with a precision of more than 87% by test to improve the simulation effect and explore the application of DL. The BLSTM-CNN (Bi-directional Long Short-Term Memory-Convolutional Neural Network) model with a precision of 95.8%, which integrates RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network) in parallel, solves the shortcomings of RNN and CNN separately. The research result can provide a more reasonable prediction model for rural banks, and ideas for the development of rural informatization and promoting rural governance.

Sign in / Sign up

Export Citation Format

Share Document