Artificial Neural Network

Karanka, J., & Luque, D. (2004). Predicting collision: a connectionist model. In H. Bowman & C. Labiousse (Eds.), Connectionist Models of Cognition and Perception II (pp. 39 -48). London: World Scientific.

by David Luque Ruiz

TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS

by Juliano Mota

Publication on ICAART 2012, Vilamoura - Algarve - Portugal.

Erkennung von Hangrutschungssystemen mit neuronalen Netzen als Grundlage für Georisikoanalysen

by Tomas Fernandez-Steeger

Fernandez-Steeger, T.M. (2002): Erkennung von Hangrutschungssystemen mit Neuronalen Netzen als Grundlage für Georisikoanalysen.- Diss. Fak. f. Bio- und Geowissenschaften Univ. Karlsruhe , Karlsruhe .

Im Rahmen von Risikoanalysen spielt die Kenntnis über das Vorhandensein und die Lage von Gefahrenherden eine ganz... more Im Rahmen von Risikoanalysen spielt die Kenntnis über das Vorhandensein und die Lage von Gefahrenherden eine ganz wesentliche Rolle. Neben den bisher bekannten deterministischen und statistischen Verfahren können auch künstliche Neuronale Netze zur automatischen Gefahrenerkennung genutzt werden. Der Vorteil Neuronaler Netze liegt in ihrer Fähigkeit begründet, nichtlineare Zusammenhänge gut darzustellen und mit sehr großen Datenmengen gut zurechtzukommen. Für die Erkennung von Hangrutschungsgebieten sind mehrere neuronale Modelle entwickelt und untersucht worden. Eine Besonderheit ist, dass die Netze verschiedene Massenbewegungstypen erkennen können. Es wird auch nicht nur die Rutschung sondern der ganze Einflussbereich der Massenbewegung erkannt. Bei der Entwicklung der Netze sind verschiedene Strategien verfolgt worden. Neben Netzen zur Rutschungserkennung sind in Reihe geschaltete Netze und nach dem MTL–Ansatz trainierte Netze untersucht worden. Dabei hat sich gezeigt, dass die einzelnen Modelle z.T. unterschiedliche Spezialisierungen entwickeln. Bei Versuchen mit den Netzen Rutschungen in Testgebieten in den Ostalpen zu erkennen, haben die besten Netze bis zu 86% der Gebiete richtig klassifiziert. Dabei hat sich gezeigt, dass die Netze Massenbewegungen in Zusammenhang mit Wildbach- und Erosionsprozessen besonders gut erkennen können. Durch gezielte Abfragen konnten die Ergebnisse auf bis zu 89 % erhöht werden.

Filtering search results using an optimal set of terms identified by an artificial neural network

by Peretz Shoval

Authors: T. Kuflik, Z. Boger, P.Shoval
Journal: Information Processing & Management (2006), Vol. 44, 469-483.

Information filtering (IF) systems usually filter data items by correlating a set of terms representing the user
s... more Information filtering (IF) systems usually filter data items by correlating a set of terms representing the user
s interest (a user profile) with similar sets of terms representing the data items. Many techniques can be employed for constructing user profiles automatically, but they usually yield large sets of term. Various dimensionality-reduction techniques can be applied in order to reduce the number of terms in a user profile. We describe a new terms selection technique including a dimensionality-reduction mechanism which is based on the analysis of a trained artificial neural network (ANN) model. Its novel feature is the identification of an optimal set of terms that can classify correctly data items that are relevant to a user. The proposed technique was compared with the classical Rocchio algorithm. We found that when using all the distinct terms in the training set to train an ANN, the Rocchio algorithm outperforms the ANN based filtering system, but after applying the new dimensionality-reduction technique, leaving only an optimal set of terms, the improved ANN technique outperformed both the original ANN and the Rocchio algorithm.

Directed Evolution In Silico

by Christopher Altman

Self-Organising Maps: An Objective Method for Clustering Complex Human Movement

by Peter Lamb

Lamb, P., Bartlett, R., & Robins, A.
International Journal of Computer Science in Sport, Volume 9, Edition 2, Pages 20-29, 2010.

In this study self-organising maps (SOM) were used to classify the coordination patterns of four participants... more In this study self-organising maps (SOM) were used to classify the coordination patterns of four participants performing three different types of basketball shot from different distances. The shots were the free throw, the three-point and the hook shot. The free throw and three-point shot were hypothesised to be more similar to one another than to the hook shot. The first analysis involved an analysis of trial trajectories visualised on a U-matrix. Two of the participants, unexpectedly, showed more similarity between the three-point shot and the hook shot, instead of the free throw. Where the first analysis was useful in showing aspects of the movement that were not obvious from viewing the computer animation of the original movement, a second SOM was trained on the appearance of the original trajectories and used to produce an output that shows the variability in coordination between all trials in the study. The second SOM showed groupings of the three shooting conditions which were unexpected. The second SOM technique may provide a more objective method than visual technique analysis for explaining movement patterning and structuring practice routines.

Understanding the relationship among launch variables in the golf drive using neural network visualisations

by Peter Lamb

Lamb, P. F.
Sports Biomechanics. Volume iFirst article, Pages 1-13, 2012.

The aim of this study was to identify and characterise individual differences in launch conditions measured from the... more The aim of this study was to identify and characterise individual differences in launch conditions measured from the same hole during four rounds of a professional golf tournament. Launch data from the 18th tee at the 2009 Dubai World Championship were used for the analysis. Self-organising maps (SOMs) were chosen to visualise the potentially non-linear relationship among the launch variables. Several distinctly different types of drives were identified on the Output Map. Drives which carried the furthest were not necessarily associated with the highest rates of ball speed. As indicated by carry distance, the longest drives had backspin rates of roughly 2,700 rpm, a launch angle of 11°, a straight or slightly left-to-right curving ball flight (for right-handers), and reached an apex of about 36 m. These values are specific to the 18th hole at the Dubai World Championship and differ from the general launch recommendations found in the literature.

Artificial neural networks for analyzing inter-limb coordination: the golf chip shot

by Peter Lamb

Lamb, P. F., Bartlett, R., & Robins, A.
Human Movement Science. Volume 30, Pages 1129-1143, 2011.

Motor control research relies on theories, such as coordination dynamics, adapted from physical sciences to explain... more Motor control research relies on theories, such as coordination dynamics, adapted from physical sciences to explain the emer- gence of coordinated movement in biological systems. Historically, many studies of coordination have involved inter-limb coordina- tion of relatively few degrees of freedom. This study looked at the high-dimensional inter-limb coordination used to perform the golf chip shot toward six different target distances. This study also introduces a visualization of high-dimensional coordination relevant within the coordination dynamics theoretical framework. A specific type of Artificial Neural Network (ANN), the Self- Organizing Map (SOM), was used for the analysis. In this study, the trajectory of consecutive best-matching nodes on the output map was used as a collective variable and subsequently fed into a second SOM which was used to create visualization of coordina- tion stability. The SOM trajectories showed changes in coordina- tion between movement patterns used for short chip shots and movement patterns used for long chip shots. The attractor dia- grams showed non-linear phase transitions for three out of four players. The methods used in this study may offer a solution for researchers from a coordination dynamics perspective who intend to use data obtained from discrete high-dimensional movements.

"Redes, lógicas no clásicas y neuronas. De los límites de la matematización más allá de la Física"

by Vicente Caballero de la Torre

En el presente artículo se exponen las líneas maestras de la "Teoría de Grafos" y aquellos problemas de... more En el presente artículo se exponen las líneas maestras de la "Teoría de Grafos" y aquellos problemas de corte formal que la misma teoría muestra como modelo para explicar el funcionamiento del cerebro. Las redes -concepto que dicha teoría intenta sistematizar y comprender matemáticamente- son de sumo interés para cualquiera que pretenda arrojar una cierta luz sobre el perfil que en la actualidad están tomando fenómenos tan diversos y actuales como el terrorismo, la cibernética y, por supuesto, las últimas investigaciones neurocientíficas.

Cooperative Behavior of Artificial Neural Agents Based on Evolutionary Architectures

by Piero Savastano

Adaptive AI Players Strategy for FPS games

by Urjit Singh Bhatia

"Conexionismo. Una útil herramienta para otras ciencias y un problemático modelo para la Psicología"

by Vicente Caballero de la Torre

Vicente CABALLERO DE LA TORRE y Francisco José ROBLES RODRÍGUEZ

Cuando se habla de “conexionismo” o “teoría conexionista” nos estamos refiriendo a una rama de las Neurociencias y de... more Cuando se habla de “conexionismo” o “teoría conexionista” nos estamos refiriendo a una rama de las Neurociencias y de las Ciencias cognitivas que surgió hace algunas décadas como alternativa minoritaria a la IA (inteligencia artificial). Las redes neuronales artificiales fueron originalmente un intento de simulación abstracta de los sistemas nerviosos biológicos. Sin embargo, no es fácil que haya un modelo completamente satisfactorio. Como conclusión se afirma que la Teoría de redes
y la Psicología cognitiva se desarrollan al margen de una serie de cuestiones filosóficamente problemáticas pensando, quizá, que se podrá dar cuenta de ellas cuando el problema de fondo (la relación mente-cerebro) se haya resuelto.

Palabras clave: “teoría conexionista”, “neurociencias”, “modelo”, “inteligencia artificial”, “problema mente-cerebro”.

A Neural Network Architecture for High-Speed Database Query Processing

by Vasant Honavar

Analysis of Decision Boundaries Generated by Constructive Neural Network Learning Algorithms

by Vasant Honavar

A Simple Randomized Quantization Algorithm for Neural Network Pattern Classifiers

by Vasant Honavar

A Neural Memory Architecture for Content as well as Address-Based Storage and Recall: Theory and Applications

by Vasant Honavar

Neural Network Automata

by Vasant Honavar

Some Biases for Efficient Learning of Spatial, Temporal, and Spatio-Temporal Patterns

by Vasant Honavar

Klasifikasi Suku Dunia Menggunakan Backpropagation

by Uki Wardoyo

Sympathetic current oscillations at an enzyme electrode induced by potential oscillations at a Pt surface

by Benjamin Wilson

B. P. Wilson, K. Yliniemi, L. Murtomäki, K. Kontturi, Electrochemistry Communications 11 (12), pp. 2328-2331

A dual-electrode set-up is introduced in order to demonstrate that electrochemical oscillations at one electrode can... more A dual-electrode set-up is introduced in order to demonstrate that electrochemical oscillations at one electrode can induce sympathetic oscillations at the other electrode. A pure Pt surface is used as a primary electrode at which the potential oscillations of the [Fe(CN)6]3- system with convective feedback occur and stimulate current oscillations at a Pt or glucose oxidase enzyme (GOD) + tetraethyl silicate (TEOS) coated electrode placed in the vicinity. The current density of the primary electrode and glucose concentration can be used to influence the frequency and amplitude of oscillations at the GOD + TEOS electrode.