A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications
da Silva, Leonardo Enzo Brito, Elnabarawy, Islam, Wunsch, Donald C. II
This survey samples from the ever-growing family of adaptive resonance theory (ART) neural network models used to perform the three primary machine learning modalities, namely, unsupervised, supervised and reinforcement learning. It comprises a representative list from classic to modern ART models, thereby painting a general picture of the architectures developed by researchers over the past 30 years. The learning dynamics of these ART models are briefly described, and their distinctive characteristics such as code representation, long-term memory and corresponding geometric interpretation are discussed. Useful engineering properties of ART (speed, configurability, explainability, parallelization and hardware implementation) are examined along with current challenges. Finally, a compilation of online software libraries is provided. It is expected that this overview will be helpful to new and seasoned ART researchers.
May-3-2019
- Country:
- Europe
- Netherlands > South Holland
- Dordrecht (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Netherlands > South Holland
- North America > United States
- California > San Mateo County
- San Mateo (0.04)
- Gulf of Mexico > Central GOM (0.04)
- Massachusetts
- Middlesex County > Cambridge (0.04)
- Plymouth County > Norwell (0.04)
- Missouri > Phelps County
- Rolla (0.04)
- New York > New York County
- New York City (0.04)
- Texas > Grayson County (0.04)
- California > San Mateo County
- Oceania > New Zealand (0.04)
- South America > Brazil
- Federal District > Brasília (0.04)
- Europe
- Genre:
- Overview (1.00)
- Research Report (1.00)
- Industry:
- Education > Educational Setting (0.67)
- Government (1.00)
- Health & Medicine (0.92)
- Leisure & Entertainment > Games
- Computer Games (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Cognitive Science (1.00)
- Machine Learning
- Learning Graphical Models > Directed Networks
- Bayesian Learning (1.00)
- Neural Networks (1.00)
- Statistical Learning > Clustering (1.00)
- Learning Graphical Models > Directed Networks
- Representation & Reasoning > Uncertainty
- Bayesian Inference (0.92)
- Fuzzy Logic (1.00)
- Information Technology > Artificial Intelligence