! Aware: default selections: Neural Network

- Given the current pace of advances in artificial intelligence and neural computing, the possibility of building smart machines that could compete with human intelligence now seems more likely than ever. Many researchers believe that artificial consciousness is possible and that, in the future, it will emerge in complex computing machines. The strongest motivation for constructing a self-aware machine is the innate human desire to discover new horizons and enlarge science's frontiers. Further, developing an artificial brain based on biological brain principles would open the door to immortality. Freed from a fragile and degradable body, a being with synthetic organs, including an artificial brain, could represent humanity's next evolutionary step. Such a new species could quickly colonize the universe, search for alien civilizations, survive to the death of the solar system, control the energy of black holes, and move at the speed of light by transmitting to other planets the information necessary for replication. As has proven the case with all important human discoveries, the real problem will be keeping technology under control. Should self-aware computers become possible, we must ensure that we use them for human progress and not for catastrophic aims.

Toward Things That Think for the Next Millennium ( Janet Wilson ; IEEE Computer Magazine 2000-01)

- Things that think will help people realize the true benefits and potential of computing, but only if those who develop technology change the way they think about computing and computing devices.

Have We Witnessed a Real-Life Turing Test? ( Marina Krol ; IEEE Computer Magazine 1999-03)

- Did Deep Blue ace the Turing Test? Did it do much more? It seems that the IBM creation not only beat the reigning World Champion Gary Kasparov, but also took a large step, in some people's eyes, toward true artificial intelligence.

Neural Interfaces Link the Mind and the Machine ( John Charles ; IEEE Computer Magazine 1999-01)

Symbolic Representation of Neural Networks ( Rudy Setiono, Huan Liu ; IEEE Computer Magazine 1996-03)

- Neural networks often surpass decision trees in predicting pattern classifications, but their predictions cannot be explained. This algorithm's symbolic representations make each prediction explicit and understandable.

Guest Editors' Introduction: Neurocomputing - Motivation, Models, and Hybridization ( Sankar K. Pal, Pradip K. Srimani ; IEEE Computer Magazine 1996-03)

Simulating Artificial Neural Networks on Parallel Architectures ( Nikola B. $\rm\check Serbed\check zija$ ; IEEE Computer Magazine 1996-03)

- Parallelization is necessary to cope with the high computational and communication demands of neuroapplications, but general-purpose parallel machines soon reach performance limitations.

An Artificial Neural Network that Models Human Decision Making ( Chew Lim Tan, Tong Seng Quah, Hoon Heng Teh ; IEEE Computer Magazine 1996-03)

- The Neural Logic Network system models a wide range of human decision-making behaviors by combining the strengths of rule-based expert systems and neural networks.

Spert-II: A Vector Microprocessor System ( John Wawrzynek, Krste $\rm Asanovi\acute c$, Brian Kingsbury, David Johnson, James Beck, Nelson Morgan ; IEEE Computer Magazine 1996-03)

- The Spert-II fixed-point vector microprocessor system performs training and recall faster than commercial workstations for neural networks used in speech recognition research.

Global Optimization for Neural Network Training ( Yi Shang, Benjamin W. Wah ; IEEE Computer Magazine 1996-03)

- This training method combines global and local searches to find a good local minimum. In benchmark comparisons against the best global optimization algorithms, it demonstrates superior performance improvement.

Artificial Neural Networks: A Tutorial ( Anil K. Jain, Jianchang Mao, K.m. Mohiuddin ; IEEE Computer Magazine 1996-03)

- These massively parallel systems with large numbers of interconnected simple processors may solve a variety of challenging computational problems. This tutorial provides the background and the basics.

The Challenge of Artificial Intelligence ( Raj Reddy ; IEEE Computer Magazine 1996-010)

- AI is a relatively young discipline, yet it has already led to general-purpose problem-solving methods and novel applications. Ultimately, AI's goals of creating models and mechanisms of intelligent action can be realized only in the broader context of computer science.

The Challenges of Real-Time AI ( David J. Musliner, James A. Hendler, Ashok K. Agrawala, Edmund H. Durfee, Jay K. Strosnider, C.j. Paul ; IEEE Computer Magazine 1995-01)

- This article examines the emerging research area of real-time artificial intelligence, surveying new approaches that combine the best of both fields and describing some important applications.

An associative architecture for genetic algorithm-based machine learning ( Kirk Twardoswski ; IEEE Computer Magazine 1994-11)

- Machine-based learning will eventually be applied to solve real-world problems. In this work, an associative architecture teams up with hybrid AI algorithms to solve a letter prediction problem with promising results. This article describes an investigation and simulation of a massively parallel learning classifier system (LCS) that was developed from a specialized associative architecture joined with hybrid AI algorithms. The LCS algorithms were specifically invented to computationally match a massively parallel computer architecture, which was a special-purpose design to support the inferencing and learning components of the LCS. The LCS's computationally intensive functions include rule matching, parent selection, replacement selection and, to a lesser degree, data structure manipulation.

Genetic algorithms: A Survey ( M. Srinivas, Lalit M. Patnaik ; IEEE Computer Magazine 1994-06)

- Genetic algorithms provide an alternative to traditional optimization techniques by using directed random searches to locate optimal solutions in complex landscapes. We introduce the art and science of genetic algorithms and survey current issues in GA theory and practice. We do not present a detailed study, instead, we offer a quick guide into the labyrinth of GA research. First, we draw the analogy between genetic algorithms and the search processes in nature. Then we describe the genetic algorithm that Holland introduced in 1975 and the workings of GAs. After a survey of techniques proposed as improvements to Holland's GA and of some radically different approaches, we survey the advances in GA theory related to modeling, dynamics, and deception.

Genetic-Algorithm Programming Environments ( Jos� L. Ribiero Filho, Philip C. Treleaven, Cesare Alippi ; IEEE Computer Magazine 1994-06)

- This review classifies genetic-algorithm environments into application-oriented systems, algorithm-oriented systems, and toolkits. It also presents detailed case studies of leading environments. Following Holland's (1975) original genetic algorithm proposal, many variations of the basic algorithm have been introduced. However. an important and distinctive feature of all GAs is the population-handling technique. The original GA adopted a generational replacement policy, according to which the whole population is replaced in each generation. Conversely, the steady-state policy used by many subsequent GAs selectively replaces the population. After we introduce GA models and their programming, we present a survey of GA programming environments. We have grouped them into three major classes according to their objectives: application-oriented systems hide the details of GAs and help users develop applications for specific domains; algorithm-oriented systems are based on specific GA models; and toolkits are flexible environments for programming a range of GAs and applications. We review the available environments and describe their common features and requirements. As case studies, we select some specific systems for more detailed examination. To conclude, we discuss likely future developments in GA programming environments.

Distributed Artificial Intelligence for Runtime Feature-Interaction Resolution ( Hugo Velthuijsen ; IEEE Computer Magazine 1993-08)

- The feature-interaction problem has many different instances. It is argued that some instances lend themselves to a distributed artificial intelligence (DAI) approach. The use of DAI techniques in current telecommunications systems appears quite natural in light of two trends in the way these systems are designed: the distribution of functionality and the incorporation of intelligence. The author illustrates the relevance of DAI techniques to the feature-interaction problem by discussing existing work (lodes, team-CPS, multistage negotiation, and negotiating agents) that address one or more instances of the problem. He further identifies the kind of cooperation and coordination that the feature-interaction problem requires and the interesting research problems it poses to distributed artificial intelligence.

Machine Intelligence-The Animat Path to Intelligent Adaptive Behaviour ( P.M. Todd ; IEEE Computer Magazine 1992-11)

- The animat path to artificial intelligence (AI), a bottom-up approach to creating intelligent systems, is described. Using this approach, artificial creatures or agents animats are constructed in an environment. They begin simply and are gradually made more and more complex, exhibiting more and more complex behaviors at each step. The goals and accomplishments of five research projects incorporating the animat path to AI methodology are reviewed.

Guest Editor's Introduction: Computer Architectures for Intelligent Systems ( ; IEEE Computer Magazine 1992-05)

- No abstract available.

(Partial list shown.)
[Complete List of Articles]

Questions and Answers: Showing

Recommendations for Neural Network Modeling Software? [2001/05/04]

At Ask Slashdot

Usable Neural Network Libraries? [ 2000/04/10]

At Ask Slashdot

Open Source Neural Networks? [ 1999/06/23]

At Ask Slashdot

Groovy Java Genetic Programming - A strongly-typed genetic programming experimentation platform written in pure Java. {(L)GPL}

At Sourceforge ( Production/Stable)

gnomekiss-1.2 - GNOME version of Kisekae Set System

At FreeBSD Ports

p5-Statistics-LTU-2.8 - Perl implementation of Linear Threshold Units

At FreeBSD Ports

snns-4.2 - Fully featured neural network simulator

At FreeBSD Ports

avida-1.6.0 - Avida is an auto-adaptive genetic system designed for ALife research

At FreeBSD Ports

javanns-1.0.b - Fully featured neural network simulator

At FreeBSD Ports

infer - Inference engine + demo {oss}

At comp.sources.unix at UUNET

Applications and Utilities

Others not displayed here

Full List

p5-AI-NeuralNet-Mesh-0.44 - A perl module implementing an optimized, accurate neural network mesh

At FreeBSD Ports

p5-AI-NeuralNet-BackProp-0.89 - Perl module implementing a back-propagation feed-forward neural network

At FreeBSD Ports

libneural-1.0.3 - C++ implementation of the classic 3-layer perceptron in library form

At FreeBSD Ports

Statistics::LTU - A module for manipulating Linear Threshold Units, also called perceptrons, which are neural networks with no hidden layers. Also see the Neural module. [Perl] {oss}

At CPAN

Neural - Artificial neural networks with backpropagation. Also see the Statistics::LTU module. [Perl] {oss}

At CPAN

Libraries and Functions

Others not displayed here

Full List

Related Subjects (default selections)

(The following links to subjects at this site retain your personalized selections.)

Up to Activity specific - Gateway topic to software used in specific activities. (application software, business, professional, science, education, etc.)

(There may be additional related subject pages listed here)

External Categories

freshmeat.net : Topic : Scientific/Engineering : Artificial Intelligence

Computers : Artificial Intelligence :

Computers : Artificial Intelligence : Neural Networks :

Computers : Artificial Life :

(Metalab at UNC) /pub/linux/devel/ai/ - tools for developing AI applications

(Metalab at UNC) /pub/linux/science/ai/ - artificial intelligence applications and simulations

(Metalab at UNC) /pub/linux/science/ai/life/ - the game of Life and other cellular automata

Personalized Selections

Platform:
Unix/BSD/Linux.
X.
MS Windows. Prog.Language:
C/C++.
Perl.
Java.
PHP. License:
Open-source.
GPL or LGPL.
Artistic. Maturity:
Stable.
Pre-production.

Tip: To exclude choices, select all others in same column

Pre-Selections

Use our system: Bring Rapid Knowledge Transfer and Awareness to your company website!

Rapid-Links: Search | About | Comments | Submit Path: RocketAware > Activity specific > Computers and Systems > Neural Net >

Personalized Selections
Platform: Unix/BSD/Linux. X. MS Windows.	Prog.Language: C/C++. Perl. Java. PHP.	License: Open-source. GPL or LGPL. Artistic.	Maturity: Stable. Pre-production.
Tip: To exclude choices, select all others in same column
Pre-Selections

Use our system: Bring Rapid Knowledge Transfer and Awareness to your company website!

Neural Network

(Partial list shown.)[Complete List of Books]

See Also

(Partial list shown.)[Complete List of Articles]

Applications and Utilities

Libraries and Functions

(Partial list shown.)
[Complete List of Books]

(Partial list shown.)
[Complete List of Articles]