Adaptive Resonance Theory (ART) is a neural network model developed by Stephen Grossberg and Gail Carpenter to explain how the brain processes information. ART networks use unsupervised and supervised learning and can perform tasks like pattern recognition and prediction. The basic ART system consists of a comparison field, recognition field, vigilance parameter, and reset module. The recognition field contains neurons that match the input vector. If the best matching neuron exceeds the vigilance parameter, learning occurs via resonance; otherwise, the neuron is inhibited and a new match is sought. ART has applications in areas like face recognition, image compression, and medical diagnosis.