TAILIEUCHUNG - Linear neurons and their learning algorithms

In this paper, we introduce the concepts of Linear neurons, and new learning algorithms based on Linear neurons, with an explanation of the reasons behind these algorithms. First, we briefly review the Boltzmann Machine and the fact that the invariant distributions of the Boltzmann Machine generate Markov chains. We then review the θ-transformation and its completeness, . any function can be expanded by θ-transformation. We further review ABM (Attrasoft Boltzmann Machine). | Journal of Computer Science and Information Technology December 2018, Vol. 6, No. 2, pp. 1-14 ISSN: 2334-2366 (Print), 2334-2374 (Online) Copyright © The Author(s). All Rights Reserved. Published by American Research Institute for Policy Development DOI: URL: Linear Neurons and Their Learning Algorithms Ying Liu1 Abstract In this paper, we introduce the concepts of Linear neurons, and new learning algorithms based on Linear neurons, with an explanation of the reasons behind these algorithms. First, we briefly review the Boltzmann Machine and the fact that the invariant distributions of the Boltzmann Machine generate Markov chains. We then review the θ-transformation and its completeness, . any function can be expanded by θ-transformation. We further review ABM (Attrasoft Boltzmann Machine). The invariant distribution of the ABM is a θtransformation; therefore, an ABM can simulate any distribution. We then discuss that the ABM algorithm is only the first algorithm in a family of new algorithms based on the θ-transformation. We introduce the simplest algorithm in this family based on Linear neurons. We also discuss the advantages of this algorithm: accuracy, stability, and low time complexity. Keywords: AI, Boltzmann machine, Markov chain, invariant distribution, Completeness, Deep Neural Network. 1. Introduction Neural networks and deep learning currently provide the best solutions to many supervised learning problems. In 2006, a publication by Hinton, Osindero, and Teh [1] introduced the idea of a “deep” neural network, which first trains a simple supervised model; then adds on a new layer on top and trains the parameters for the new layer alone. You keep adding layers and training layers in this fashion until you have a deep network. Later, this condition of training one layer at a time is removed. After Hinton‟s initial attempt of training one layer at a time, Deep Neural Networks train all layers .

• Toán học
• Journal of computer science and information technology
• Linear neurons and their learning algorithms
• Deep neural network
• Attrasoft boltzmann machine
• The Boltzmann Machine generate Markov chains
• Global journal of computer science
• Global journal of computer science and technology
• Information & technology
• GIS based fire emergency response system
• International Journal of Computer Science and Communication Networks
• Intelligent public transport system
• Information forensics and security
• Wi Fi or GPRS technology
• Intelligent Public Transport Information System
• Identifying the Technology of a Bronze Dagger Discovered
• in Espidezh Region of Bazman in Sistan
• X ray diffraction
• Scanning electron microscope
• Journal of Computer Science and Cybernetics
• Automatic identification of Vietnamese dialects
• Faculty of Information Technology
• Gaussian Mixture Model
• Mel frequency Cepstral Coefficients
• Journal of technology and science education
• An uCASE CL model implementation
• Strengthen the academic learning
• Information and communication technologies
• Computer Aided Software Engineering
• Predicting attendance at major league soccer matches
• A comparison of four techniques
• Out of sample root mean square error statistics
• The efficacy of contemporary algorithms
• The quadratic entropy approach
• Implement the ID3 decision tree algorithm
• The Shannon entropy formula
• The traditional ID3 implementation
• A scalable attack graph generation
• Network security management
• The security risk management
• The network systems
• Convolutional neural network application in biomedical signals
• Convolutional neural network application
• Identify the future research direction
• Recent improvements in big data
• Forked communication network model
• Non homogenous bulk arrivals
• Phase type transmission
• Non homogenous compound Poisson process
• Historical archaeology among the Villages
• The Villages of southern Jordan
• Modern economic potential
• The occupation history
• Voices from the pas
• Conceptualizing a “Fifth World”
• Larger contemporary states
• Fourth World groups appears
• Vegetable storage practices
• The reproduction of household autonomy
• Early village contexts from northwest Argentina
• Early Village Societies
• Archaeoastronomy at Kanda geoglyph
• Alexander the Great
• Likely burial chambers
• Inside the mound
• Paleoindian solar and stellar pictographic trail
• The monte alegre hills of Brazil
• Implications for pioneering new landscapes
• The tropical forests
• Nicosia city plans in the Ottomans era
• An archaeological civilized study
• The natural environment
• Security factors on Nicosias districts
• Tace elements in eneolithic
• Late medieval human bones
• Two archaeological sites in tuscany
• Evaluation of diagenetic processes
• Diet and exposure to heavy metals
• A model of ICT acceptance
• Higher education institutions
• Retraining on ICT programmes
• Information and communications Technology