scholarly journals Federated transfer learning: Concept and applications

2021 ◽  
Vol 15 (1) ◽  
pp. 35-44
Author(s):  
Sudipan Saha ◽  
Tahir Ahmad
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Transfer Learning ◽  
User Privacy ◽  
Comprehensive Survey ◽  
Further Development ◽  
Learning Concept ◽  
Limited Scope

Development of Artificial Intelligence (AI) is inherently tied to the development of data. However, in most industries data exists in form of isolated islands, with limited scope of sharing between different organizations. This is an hindrance to the further development of AI. Federated learning has emerged as a possible solution to this problem in the last few years without compromising user privacy. Among different variants of the federated learning, noteworthy is federated transfer learning (FTL) that allows knowledge to be transferred across domains that do not have many overlapping features and users. In this work we provide a comprehensive survey of the existing works on this topic. In more details, we study the background of FTL and its different existing applications. We further analyze FTL from privacy and machine learning perspective.

scholarly journals Federated Reinforcement Distillation with Proxy Experience Memory

2020 ◽  
Author(s):  
Han Cha ◽  
Jihong Park ◽  
Hyesung Kim ◽  
Seong-Lyun Kim ◽  
Mehdi Bennis
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Data Confidentiality ◽  
User Privacy ◽  
Joint Conference ◽  
International Joint

This paper is presented at 28th International Joint Conference on Artificial Intelligence (IJCAI-19) 1st Wksp. Federated Machine Learning for User Privacy and Data Confidentiality (FML'19), Macau, August 2019.

scholarly journals Transfer Learning and Deep Domain Adaptation

2020 ◽  
Author(s):  
Wen Xu ◽  
Jing He ◽  
Yanfeng Shu
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Transfer Learning ◽  
Real World ◽  
Deep Neural Networks ◽  
Domain Adaptation ◽  
Fine Tuning ◽  
Real World Applications ◽  
Comprehensive Survey ◽  
Sample Reconstruction

Transfer learning is an emerging technique in machine learning, by which we can solve a new task with the knowledge obtained from an old task in order to address the lack of labeled data. In particular deep domain adaptation (a branch of transfer learning) gets the most attention in recently published articles. The intuition behind this is that deep neural networks usually have a large capacity to learn representation from one dataset and part of the information can be further used for a new task. In this research, we firstly present the complete scenarios of transfer learning according to the domains and tasks. Secondly, we conduct a comprehensive survey related to deep domain adaptation and categorize the recent advances into three types based on implementing approaches: fine-tuning networks, adversarial domain adaptation, and sample-reconstruction approaches. Thirdly, we discuss the details of these methods and introduce some typical real-world applications. Finally, we conclude our work and explore some potential issues to be further addressed.

scholarly journals Image Classification Using Reinforcement Learning

2020 ◽  
Vol 23 (6) ◽  
pp. 1172-1191
Author(s):  
Artem Aleksandrovich Elizarov ◽  
Evgenii Viktorovich Razinkov
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Computer Vision ◽  
Reinforcement Learning ◽  
Image Classification ◽  
Deep Neural Network ◽  
Learning Algorithms ◽  
Further Development

Recently, such a direction of machine learning as reinforcement learning has been actively developing. As a consequence, attempts are being made to use reinforcement learning for solving computer vision problems, in particular for solving the problem of image classification. The tasks of computer vision are currently one of the most urgent tasks of artificial intelligence. The article proposes a method for image classification in the form of a deep neural network using reinforcement learning. The idea of ​​the developed method comes down to solving the problem of a contextual multi-armed bandit using various strategies for achieving a compromise between exploitation and research and reinforcement learning algorithms. Strategies such as -greedy, -softmax, -decay-softmax, and the UCB1 method, and reinforcement learning algorithms such as DQN, REINFORCE, and A2C are considered. The analysis of the influence of various parameters on the efficiency of the method is carried out, and options for further development of the method are proposed.

scholarly journals Complex Scene Understanding and Recognition Based on the Explainable Machine Learning in AI Models

2021 ◽  
Author(s):  
Bin Wu ◽  
Yuhong Fan ◽  
Yeh-Cheng Chen ◽  
Tao Zhang
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
Network Model ◽  
Scene Understanding ◽  
Learning Model ◽  
Small Sample ◽  
Theoretical Research ◽  
Optimization Efficiency

Abstract Information fusion is an important part of numerous neural network systems and other machine learning models. However, there exist some problems about fusion in scene understanding and recognition of complex environment, such as difficulty in feature extraction, small sample size and interpretability of the model. Deep reinforcement learning can combine the perception ability of deep learning with the decision-making ability of reinforcement learning to learn control strategies directly from high-dimensional original data. However, It faces these challenges, such as low optimization efficiency, poor generality of network model, small labeled samples, explainable decisions for users without a strong background on Artificial Intelligence (AI). Therefore, at the level of application and theoretical research, this paper aims to solve the above problems,the main contributions include: (1)optimize the feature representation methods based on spatial-temporal feature of the behavior characteristics in the scene, deep metric learning between adjacent layers and cross-layer learning theory, and then propose a lightweight reinforcement learning network model to solve these problems of the complexity of the model to be explained, the difficulty of extracting feature and the difficulty of tuning parameter; (2)construct the self-paced learning strategy of the deep reinforcement learning model, introduce transfer learning mechanism in the optimization process, and solve the problem of low optimization efficiency and small labeled samples; (3)design the behavior recognition framework of the multi-perspective deep knowledge transfer learning model, construct a explainable behavior descriptor, and solve the problems of poor network generality and weak 1explanation of network. Our research is of great theoretical and practical significance in the fields of artificial intelligence and public security.

scholarly journals New technologies for tourist services market development

2020 ◽  
pp. 113-116
Author(s):  
O. V. Shpyrnya ◽  
M. V. Koreneva
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Business Processes ◽  
New Technologies ◽  
Market Development ◽  
Trip Planning ◽  
Tourism Product ◽  
Use Of Internet ◽  
Tourism Services ◽  
Further Development

This article analyzes the introduction of new technologies in the tourist services market. It has been determined that at present tourist enterprises are actively investing money in the process of introducing machine learning and artificial intelligence technologies; actively use automation of various levels of complexity of business processes. It is concluded that the sales technologies of the tourism product and individual tourism services are based today on the intensive implementation of modern technological solutions. It is noted that the main trends in the development of the tourist services market will be the further development of online tourism in Russia, as well as the widespread use of Internet technologies.Further penetration of technologies that simplify the routine operations of tourists is predicted. This, for example, real-time luggage tracking via phone, combining trip planning and booking services in one application. At the same time, it will be implemented in the B2B segment. New tourist platforms are being developed today, in which all content from a wide variety of sources is presented, whether it is the traditional GDS, NDC booking system, airline’s own APIs or aggregator data.

scholarly journals Building trust when using artificial intelligence

E-Management ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 28-36
Author(s):  
A. A. Dashkov ◽  
Yu. O. Nesterova
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Information And Communication Technologies ◽  
Communication Technologies ◽  
Learning Systems ◽  
Building Trust ◽  
Information And Communication ◽  
Continuous Progress ◽  
The Impact ◽  
Further Development

In the XXI century, “trust” becomes a category that manifests itself in a variety of ways and affects many areas of human activity, including the economy and business. With the development of information and communication technologies and end-to-end technologies, this influence is becoming more and more noticeable. A special place in digital technologies is occupied by human trust when interacting with artificial intelligence and machine learning systems. In this case, trust becomes a potential stumbling block in the field of further development of interaction between artificial intelligence and humans. Trust plays a key role in ensuring recognition in society, continuous progress and development of artificial intelligence.The article considers human trust in artificial intelligence and machine learning systems from different sides. The main objectives of the research paper are to structure existing research on this subject and identify the most important ways to create trust among potential consumers of artificial intelligence products. The article investigates the attitude to artificial intelligence in different countries, as well as the need for trust among users of artificial intelligence systems and analyses the impact of distrust on business. The authors identified the factors that are crucial in the formation of the initial level of trust and the development of continuous trust in artificial intelligence.

How Artificial Intelligence, Machine Learning and Deep Learning are Radically Different?

2018 ◽  
Vol 8 (2) ◽  
pp. 1
Author(s):  
Tanya Tiwari ◽  
Tanuj Tiwari ◽  
Sanjay Tiwari
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Analysis Software ◽  
Science Data ◽  
Human Machine Interaction ◽  
Learning Techniques ◽  
Nested Hierarchy ◽  
Further Development ◽  
Machine Interaction

There is a lot of confusion these days about Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL). A computer system able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. Artificial Intelligence has made it possible. Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. In other words, all machine learning is AI, but not all AI is machine learning, and so forth. Machine Learning represents a key evolution in the fields of computer science, data analysis, software engineering, and artificial intelligence. Machine learning (ML)is a vibrant field of research, with a range of exciting areas for further development across different methods and applications. These areas include algorithmic interpretability, robustness, privacy, fairness, inference of causality, human-machine interaction, and security. The goal of ML is never to make “perfect” guesses, because ML deals in domains where there is no such thing. The goal is to make guesses that are good enough to be useful. Deep learning is a particular kind of machine learning that achieves great power and flexibility by learning to represent the world as nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations computed in terms of less abstract ones. This paper gives an overview of artificial intelligence, machine learning & deep learning techniques and compare these techniques.

scholarly journals Federated Reinforcement Distillation with Proxy Experience Memory

2020 ◽  
Author(s):  
Han Cha ◽  
Jihong Park ◽  
Hyesung Kim ◽  
Seong-Lyun Kim ◽  
Mehdi Bennis
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Data Confidentiality ◽  
User Privacy ◽  
Joint Conference ◽  
International Joint

This paper is presented at 28th International Joint Conference on Artificial Intelligence (IJCAI-19) 1st Wksp. Federated Machine Learning for User Privacy and Data Confidentiality (FML'19), Macau, August 2019.

CONTENT OF TEACHING THE ELEMENTS OF ARTIFICIAL INTELLIGENCE IN A SCHOOL INFORMATICS COURSE

2020 ◽  
pp. 3-10
Author(s):  
I. V. Levchenko
Keyword(s):  
Artificial Intelligence ◽  
General Education ◽  
Extracurricular Activities ◽  
Information Technologies ◽  
Learning Experience ◽  
9Th Grade ◽  
Modern Information ◽  
Further Development ◽  
Form Variant ◽  
Theoretical Foundations

The article considers the feasibility of integrating artificial intelligence technologies into school education and identifies a problem in identifying didactic elements in the field of artificial intelligence, which must be mastered in a school informatics course. The purpose of the article is to propose variant of the content of teaching the elements of artificial intelligence for the general education of schoolchildren as part of the curricular and extracurricular activities in informatics. An analysis of the psychological, pedagogical and scientific-methodical literature in the field of artificial intelligence made it possible to identify the appropriateness of teaching schoolchildren the elements of artificial intelligence in the framework of a comprehensive informatics course, as the theoretical foundations of modern information technologies. Summarizing and systematizing the learning experience of schoolchildren in the field of artificial intelligence made it possible to form variant of the content of teaching the elements of artificial intelligence, which can be implemented in a compulsory informatics course for 9th grade, as well as in elective classes. The results of the study are the theoretical basis for the further development of the components of the methodological system of teaching the elements of artificial intelligence in a school informatics course. The research materials may be useful to specialists in the field of teaching informatics and to informatics teachers.

Machine Learning in Agriculture

2018 ◽  
Vol 8 (6) ◽  
pp. 26 ◽  
Author(s):  
Matthew N. O. Sadiku ◽  
Chandra M. M Kotteti ◽  
Sarhan M. Musa
Keyword(s):  
Climate Change ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Disease Diagnosis ◽  
Automated Detection ◽  
Disease Prediction ◽  
Paper Briefly ◽  
Agriculture Sector ◽  
Modern Agriculture ◽  
Crop Disease

Machine learning is an emerging field of artificial intelligence which can be applied to the agriculture sector. It refers to the automated detection of meaningful patterns in a given data.  Modern agriculture seeks ways to conserve water, use nutrients and energy more efficiently, and adapt to climate change.  Machine learning in agriculture allows for more accurate disease diagnosis and crop disease prediction. This paper briefly introduces what machine learning can do in the agriculture sector.

Sign in / Sign up

Export Citation Format

Share Document