scholarly journals A Roadmap for the Development of the ‘SP Machine’ for Artificial Intelligence

2019 ◽  
Vol 62 (11) ◽  
pp. 1584-1604
Author(s):  
Vasile Palade ◽  
J Gerard Wolff
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Parallel Processing ◽  
Virtual Machine ◽  
Computer Model ◽  
High Performance ◽  
Theory Of Intelligence ◽  
High Performance Computer ◽  
Further Development

AbstractThis paper describes a roadmap for the development of the SP Machine, based on the SP Theory of Intelligence and its realization in the SP Computer Model. The SP Machine will be developed initially as a software virtual machine with high levels of parallel processing, hosted on a high-performance computer. The system should help users visualize knowledge structures and processing. Research is needed into how the system may discover low-level features in speech and in images. Strengths of the SP System in the processing of natural language may be augmented, in conjunction with the further development of the SP System’s strengths in unsupervised learning. Strengths of the SP System in pattern recognition may be developed for computer vision. Work is needed on the representation of numbers and the performance of arithmetic processes. A computer model is needed of SP-Neural, the version of the SP Theory expressed in terms of neurons and their interconnections. The SP Machine has potential in many areas of application, several of which may be realized on short-to-medium timescales.

МЕТОДЫ ДОСТИЖЕНИЯ МАКСИМАЛЬНОЙ ЭФФЕКТИВНОСТИ ПЛАТФОРМЫ ПРОТОТИПИРОВАНИЯ ВЫСОКОПРОИЗВОДИТЕЛЬНЫХ СИСТЕМ НА КРИСТАЛЛЕ НА ЗАДАЧАХ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА

2020 ◽  
Vol 96 (3s) ◽  
pp. 585-588
Author(s):  
С.Е. Фролова ◽  
Е.С. Янакова
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Computer Vision ◽  
High Performance ◽  
Systems On Chip ◽  
High Performance Systems ◽  
On Chip ◽  
Network Technologies ◽  
Neural Network Technologies

Предлагаются методы построения платформ прототипирования высокопроизводительных систем на кристалле для задач искусственного интеллекта. Изложены требования к платформам подобного класса и принципы изменения проекта СнК для имплементации в прототип. Рассматриваются методы отладки проектов на платформе прототипирования. Приведены результаты работ алгоритмов компьютерного зрения с использованием нейросетевых технологий на FPGA-прототипе семантических ядер ELcore. Methods have been proposed for building prototyping platforms for high-performance systems-on-chip for artificial intelligence tasks. The requirements for platforms of this class and the principles for changing the design of the SoC for implementation in the prototype have been described as well as methods of debugging projects on the prototyping platform. The results of the work of computer vision algorithms using neural network technologies on the FPGA prototype of the ELcore semantic cores have been presented.

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.

Studying an Eulerian Computer Model on Different High-performance Computer Platforms and Some Applications

2010 ◽  
Author(s):  
K. Georgiev ◽  
Z. Zlatev ◽  
Michail D. Todorov ◽  
Christo I. Christov
Keyword(s):  
Computer Model ◽  
High Performance ◽  
High Performance Computer

HBGC123D: a high-performance computer model of coupled hydrogeological and biogeochemical processes

2001 ◽  
Vol 27 (10) ◽  
pp. 1231-1242 ◽  
Author(s):  
Jin P Gwo ◽  
Eduardo F D’Azevedo ◽  
Hartmut Frenzel ◽  
Melanie Mayes ◽  
Gour-Tsyh Yeh ◽  
...  
Keyword(s):  
Computer Model ◽  
High Performance ◽  
Biogeochemical Processes ◽  
High Performance Computer

scholarly journals SISTEM PAKAR PENDIAGNOSA PENYAKIT GINJAL

2011 ◽  
Vol 11 (1) ◽  
pp. 131
Author(s):  
Luther Latumakulita ◽  
Chriestie E. J. C. Montolalu
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Expert System ◽  
Kidney Disease ◽  
Natural Language ◽  
Language Processing ◽  
Neural System ◽  
Development Environment ◽  
Microsoft Access

Sistem pakar merupakan salah satu cabang kecerdasan buatan yang mempelajari bagaimana meniru cara berpikir seorang pakar dalam menyelesaikan suatu permasalahan. Kecerdasan buatan adalah salah satu bidang ilmu komputer yang mendayagunakan komputer sehingga dapat berperilaku cerdas seperti manusia. Ilmu komputer mengembangkan perangkat lunak dan perangkat keras untuk menirukan tindakan manusia. Aktifitas manusia yang ditirukan seperti penalaran, penglihatan, pembelajaran, pemecahan masalah, pemahaman bahasa alami, dan sebagainya. Sesuai definisi, teknologi kecerdasan buatan dipelajari dalam bidang-bidang seperti Robotika (Robotics), Penglihatan Komputer (Computer Vision), Pengolahan Bahasa Alami (Natural Language Processing), Pengenalan Pola (Pattern Recognition), Sistem Syaraf Buatan (Artificial Neural System), Pengenalan Suara (Speech Recognition), dan Sistem pakar (Expert System). Sistem pakar terdiri 2 bagian pokok, yaitu lingkungan pengembangan (development environment) digunakan sebagai pembangun sistem pakar baik dari segi pembangun komponen maupun basis pengetahuan dan lingkungan konsultasi (consultation environment)digunakan oleh seseorang yang bukan ahli untuk berkonsultasi. Lingkungan pengembangan digunakan oleh ES builder untuk membangun komponen dan memasukan penetahuan kedalam basis pengetahuan. Aplikasi Sistem Pakar ini adalah merupakan paket perangkat lunak yang membahas bagaimana cara untuk mendeteksi penyakit ginjal pada manusia. Sistem pakar pendeteksi penyakit ginjal pada manusia ini terdiri atas 2 bagian yaitu : Lingkungan Konsultasi (Development environment) dan Lingkungan Pengembangan (Consultation environment). Bahasa pemrograman yang digunakan untuk membuat aplikasi system pakar ini Microsoft Visual Studio 6.0 dengan databasenya menggunakan Microsoft Access 2003. sesuai dengan bahasa pemrograman yang digunakan maka interface yang akan ditampilkan dalam memberikan informasi bagi user akan berbentuk visual. EXPERT SYSTEM FOR KIDNEY DISEASE DIAGNOSISABSTRACTExpert System (ES) is an artifial intelligence which aplicate a profesional’s way of think in solving a problem. Artificial intelligence is a computer field which move computer to operate as smart as human brain. This computer science develop software and hardware to act like a human. Human activities which modify such as reasoning, vision, learning, problem solving, natural language, etc. Base on that definition, artificial intelligence technologi were improved in many fields such as Robotics, Computer Vision, Natural Language Processing, Pattern Recognition, Artificial Neural System, Speech Recognition, and Expert System. Expert System consist of two main fields: development environment used as expert system builder in component builder and also knowledge base, and consultation builder used by a person who has not ability in in consultation. Development environment used by ES builder to build component and input knowledge in to the knowledge base. This Expert System Aplication is a software sistem, which improve the aplication to detect kidney disease for human. Expert System detection of kidney disease for human consists of two parts: Development environment and Consultation environment.Programming language, which used to build this Expert System aplication, is Microsoft Visual Studio 6.0 with database Microsoft Access 2003. Base on the language programming used, then the interface, to give the information for user, will be shown in visual.

A REVIEW OF FACE RECOGNITION METHODS

2013 ◽  
Vol 27 (04) ◽  
pp. 1356005 ◽  
Author(s):  
M. PARISA BEHAM ◽  
S. MOHAMED MANSOOR ROOMI
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Face Recognition ◽  
Soft Computing ◽  
Recognition Accuracy ◽  
Previous Survey ◽  
The Past ◽  
Potential Applications ◽  
Feature Based

Face recognition has become more significant and relevant in recent years owing to it potential applications. Since the faces are highly dynamic and pose more issues and challenges to solve, researchers in the domain of pattern recognition, computer vision and artificial intelligence have proposed many solutions to reduce such difficulties so as to improve the robustness and recognition accuracy. As many approaches have been proposed, efforts are also put in to provide an extensive survey of the methods developed over the years. The objective of this paper is to provide a survey of face recognition papers that appeared in the literature over the past decade under all severe conditions that were not discussed in the previous survey and to categorize them into meaningful approaches, viz. appearance based, feature based and soft computing based. A comparative study of merits and demerits of these approaches have been presented.

Sign in / Sign up

Export Citation Format

Share Document