Categories

Applications

Biological Classification: The classification of biological data.

Character Recognition: The recognition of written and printed text, or characters, using algorithms.

Chemical Analysis: Classification of a substance’s constituent elements

Financial Time Series Predictions: Financial forecasting based on the analysis of time series data using neural networks.

Human-Machine Interface: Design of terminals at which operators interact with devices by use of neural networks.

Industrial Control: The use information received from remote stations to form automated supervisory commands.

Information Fusion: The merging of information from disparate sources with differing conceptual, contextual and typographical representations.

Market Research: The systematical gathering, recording and analyzing of data about customers, competitors and the market.

Medical Diagnosis: Recognition of medical conditions, such as cancer.

Network Analysis: Patterns identification in large scale networks.

Remote Sensing: Acquisition of information using a device that is not in physical contact with the object, such as satellite or radar images.

Utilities: Code used to make code.

Other: None of the above apply.

Models

ART 1: An Adaptive Resonance Theory (ART) neural network architecture accepting binary inputs.

ART 2 / Fuzzy ART: Adaptive Resonance Theory (ART) neural network supporting continuous (analog) inputs.

ART 2-A: A streamlined form of the ART 2 network with a drastically accelerated runtime.

ART 3: An Adaptive Resonance Theory neural network which builds on ART 2 by simulating rudimentary neurotransmitter regulation of synaptic activity by incorporating simulated sodium (Na+) and calcium (Ca2+) ion concentrations into the system’s equations.

ARTMAP: ARTMAP combines two slightly modified ART-1 or ART-2 units into a supervised learning structure.

Fuzzy ARTMAP: Implements fuzzy logic into the ARTMAP architecture, enhancing generalizability.

Distributed ART: A real-time model of parallel distributed pattern learning that permits fast as well as slow adaptation, without catastrophic forgetting.

Modified ART: ART variants and modifications apart from the ones mentioned above.

Feature filling-in:

Boundary Contour System: The Boundary Contour System is a dynamic neural network model composed of shunting neurons designed to replicate the properites of illusory contour formation as observed in psychophysical studies.

Compartmental Modeling: Construction of detailed neuronal models, by dividing the neuron into a number of interconnected anatomical compartments. Each compartment is then modeled with differential equations describing an equivalent electrical circuit. With the appropriate equations for each compartment, we may model the behavior of each compartment as well as its interactions with neighboring compartments.

Genetic Algorithms: A class of evolutionary algorithms that use techniques inspired by evolutionary biology such as inheritance, mutation, selection, and crossover.

Self Organizing Maps: A type of artificial NN that is trained using unsupervised learning to produce a low-dimensional (typically two dimensional), discretized representation of the input space of the training samples, called a map.

Other: None of the above fit.

Topics

Biological Learning: Papers focusing on how biological systems learn. Topics include laminar computing, cognitive emotional interaction, and sequence learning, etc.

Biological Vision: Papers focusing on how biological systems visually perceive their surroundings. Topics include: brightness perception, motion perception, depth perception, surface perception.

Image Analysis: The extraction of information from images using neural network methods.

Machine Learning: Algorithms and techniques which allow computers to learn based of various inputs.

Mathematical Foundations of Neural Networks: Mathematical methods such as differential equations are fundamental to our understanding of Neural Networks. Papers here are devoted to direct applications of these mathematical concepts.

Neural Hardware: Specialized electronic hardware which are built to act like a network of neurons.

Robotics: The application of automated machinery to tasks traditionally done by hand, as in the manufacturing industry.

Speech and Hearing: Papers focused on speech and hearing. Topics such as speech recognition are covered.

Other: None of the above apply