A Class of Designs for a Sparse Distributed Memory
Author : Research Institute for Advanced Computer Science (U.S.)
Publisher :
Page : 46 pages
File Size : 38,13 MB
Release : 1989
Category :
ISBN :
Author : Research Institute for Advanced Computer Science (U.S.)
Publisher :
Page : 46 pages
File Size : 38,13 MB
Release : 1989
Category :
ISBN :
Author : National Aeronautics and Space Administration (NASA)
Publisher : Createspace Independent Publishing Platform
Page : 44 pages
File Size : 39,13 MB
Release : 2018-06-27
Category :
ISBN : 9781721993345
A general class of designs for a space distributed memory (SDM) is described. The author shows that Kanerva's original design and the selected-coordinate design are related, and that there is a series of possible intermediate designs between those two designs. In each such design, the set of addresses that activate a memory location is a sphere in the address space. We can also have hybrid designs, in which the memory locations may be a mixture of those found in the other designs. In some applications, the bits of the read and write addresses that will actually be used might be mostly zeros; that is, the addresses might lie on or near z hyperplane in the address space. The author describes a hyperplane design which is adapted to this situation and compares it to an adaptation of Kanerva's design. To study the performance of these designs, he computes the expected number of memory locations activated by both of two addresses. Jaeckel, Louis A. Unspecified Center NCC2-387; NCC2-408...
Author : Pentti Kanerva
Publisher :
Page : 60 pages
File Size : 47,4 MB
Release : 1992
Category : Distributed artificial intelligence
ISBN :
Abstract: "This paper describes sparse distributed memory (SDM) as a neural-net associative memory. It is characterized by two weight matrices and by a large internal dimension -- the number of hidden units is much larger than the number of input or output units. The first matrix, A, is fixed and possibly random, and the second matrix, C, is modifiable. The paper compares and contrasts SDM to (1) computer memory, (2) correlation-matrix memory, (3) feed-forward artificial neural network, (4) cortex of the cerebellum, (5) Marr and Albus models of the cerebellum, and (6) Albus' cerebellar model arithmetic computer (CMAC). Several variations of the basic SDM design are discussed: the selected-coordinate and hyperplane designs of Jaeckel, the pseudorandom associative neural memory of Hassoun, and SDM with real-valued input variables by Prager and Fallside. SDM research conducted mainly at RIACS in 1986-1991 is highlighted."
Author : Research Institute for Advanced Computer Science (U.S.)
Publisher :
Page : 54 pages
File Size : 46,30 MB
Release : 1989
Category :
ISBN :
Author :
Publisher :
Page : 1002 pages
File Size : 43,16 MB
Release : 1990
Category : Aeronautics
ISBN :
Author :
Publisher :
Page : 456 pages
File Size : 23,12 MB
Release : 1995
Category : Aeronautics
ISBN :
Author : Kohei Arai
Publisher : Springer Nature
Page : 832 pages
File Size : 40,91 MB
Release : 2022-08-30
Category : Technology & Engineering
ISBN : 303116072X
This book is a remarkable collection of chapters covering a wide domain of topics related to artificial intelligence and its applications to the real world. The conference attracted a total of 494 submissions from many academic pioneering researchers, scientists, industrial engineers, and students from all around the world. These submissions underwent a double-blind peer-reviewed process. Of the total submissions, 176 submissions have been selected to be included in these proceedings. It is difficult to imagine how artificial intelligence has become an inseparable part of our life. From mobile phones, smart watches, washing machines to smart homes, smart cars, and smart industries, artificial intelligence has helped to revolutionize the whole globe. As we witness exponential growth of computational intelligence in several directions and use of intelligent systems in everyday applications, this book is an ideal resource for reporting latest innovations and future of AI. Distinguished researchers have made valuable studies to understand the various bottlenecks existing in different arenas and how they can be overcome with the use of intelligent systems. This book also provides new directions and dimensions of future research work. We hope that readers find the volume interesting and valuable.
Author : International Joint Conferences on Artificial Intelligence
Publisher :
Page : 1056 pages
File Size : 45,2 MB
Release : 1995
Category : Artificial intelligence
ISBN :
Author :
Publisher :
Page : 1064 pages
File Size : 49,81 MB
Release : 1994
Category : Government publications
ISBN :
Author : Mohamad H. Hassoun
Publisher :
Page : 384 pages
File Size : 16,11 MB
Release : 1993
Category : Computers
ISBN :
Brings together significant works on associative neural memory theory (architecture, learning, analysis, and design) and hardware implementation (VLSI and opto-electronic) by leading international researchers. The volume is organized into an introductory chapter and four parts: biological and psychological connections, artificial associative neural memory models, analysis of memory dynamics and capacity, and implementation. Annotation copyright by Book News, Inc., Portland, OR