TAILIEUCHUNG - An improved learning algorithm of bam

In this paper, we propose a learning algorithm of BAM, which learns from training data more flexibly as well as improves the ability of recall for non-orthogonal patterns. In our learning algorithm, associations of patterns are updated flexibly in a few iterations by modifying parameters after each iteration. Moreover, the proposed learning algorithm assures the recalling of all patterns is similar, which is presented by the stop condition of the learning process. | Nông Thị Hoa và Đtg Tạp chí KHOA HỌC & CÔNG NGHỆ 113(13): 61 - 65 AN IMPROVED LEARNING ALGORITHM OF BAM Nong Thi Hoa1,*, Bui The Duy2 1 College of Information Technology and Communication – TNU 2 Human Machine Interaction Laboratory – Vietnam National University, Hanoi SUMMARY Artificial neural networks, characterized by massive parallelism, robustness, and learning capacity, have many applications in various fields. Bidirectional Associative Memory (BAM) is a neural network that is extended from Hopfield networks to make a two-way associative search for a pattern pair. The most important advantage of BAM is recalling stored patterns from noisy inputs. Learning process of previous BAMs, however, is not flexible. Moreover, orthogonal patterns are recalled better than other patterns. It means that, some important patterns cannot be recalled. In this paper, we propose a learning algorithm of BAM, which learns from training data more flexibly as well as improves the ability of recall for non-orthogonal patterns. In our learning algorithm, associations of patterns are updated flexibly in a few iterations by modifying parameters after each iteration. Moreover, the proposed learning algorithm assures the recalling of all patterns is similar, which is presented by the stop condition of the learning process. We have conduct experiments with five datasets to prove the effectiveness of BAM with the proposed learning algorithm (FBAM - Flexible BAM). Results from experiments show that FBAM recalls better than other BAMs in auto-association mode. Keywords: Bidirectional Associative Memory, Associative Memory, Learning Algorithm, Noise Tolerance, Pattern Recognition. INTRODUCTION* Artificial neural networks, characterized by massive parallelism, robustness, and learning capability, effectively solve many problems such as pattern recognition, designing controller, clustering data. BAM [1] is designed from two Hopfield neural networks to show a two-way associative search .

• Vật lý
• An improved learning algorithm of bam
• Bidirectional Associative Memory
• Non orthogonal patterns
• The proposed learning algorithm
• The learning process
• Journal of technology and science education
• Some strategies to improve the learning process
• Improve the learning process
• Matter the continent nor
• Learning process as well
• Business process management
• Business process learning
• Action learning
• Process knowledge
• Design science
• Total Quality Management
• Teaching and learning process
• Quality of teaching and learning
• Teaching quality management model
• Outline of teaching and learning process
• Extrinsic motivation of learning English
• The research learning English
• An investigation into the impact learning English
• Learning English of of students at high schools
• Learning English of of students in Hue
• Methods for motivating students
• Gamification in learning process and its impact on entrepreneurial intention
• Gamification in learning process
• Attitude towards behavior
• Perceived behavioral control
• Forming entrepreneurial intentions for students
• Social sciences
• Homeschooling in southern Thailand
• Learning process management
• Standard deviation
• Learning management systems
• Management skills
• Lecture Learning management systems
• Computer based learning
• Management system
• Process and organizational resources
• Learning management careers
• Experiential learning
• Experiential learning activities
• Design experiential learning activities
• Skill of design experiential learning activities
• Teaching biology
• Educational sciences
• Open organizational learning
• Stakeholder knowledge
• Process development
• Learning organization
• Collective intelligence
• Semantic technology
• BPM capabilities
• Reflective learning journals
• Content analysis
• Reflective journals
• Learning business
• Process management concepts
• Needs analysis in teaching learning process
• Developing teaching Arabic language syllabus
• Islamic Religion Education of STAIS Sumatera
• Needs analysis
• Learning need
• Syllabus development
• Email writing process
• High school students’ perceptions
• Process of learning to write Emails
• Write Emails in english
• Email writing skills
• Management process
• Organizational resources
• Process theories of motivation
• ICT for e learning
• Higher education institutions
• Mobile learning
• Facilitating the learning process
• HEIs in developing countries
• Decentralized authentication
• Merkle tree
• Authentication in E learning systems
• Online learning system
• Authentication process in the online learning system
• Motivation in language learning
• Students’ motivation for learning Improvement of students' motivation
• Boring learning process
• Intrinsic and extrinsic motivation
• Motivation for learning English
• Strengthen students’ motivation
• Motivation in language teaching
• Learning objectives
• Learning process in class
• Vstep on students’ learning motivation at Vietnam national uinversity
• Vstep on students’ learning motivation
• Students’ learning motivation
• Vietnamese Standardized Test of English Proficiency
• The teaching and learning process
• Generic skills development and learning assessment process
• Use of rubrics and students validation
• Generic skills development
• The academic marks
• Validaton queries and process
• Reinforcement learning
• Q Learning
• Multi agent system
• Distributed system
• Markov decision process
• Factored Markov decision process
• Technology enhanced learning
• Educational game
• Primary education
• Solar system
• Primary school learning process