Deep Learning Can’t be Trusted Brain Modelling Pioneer Says

IEEE Spectrum  December 30, 2021
The inability of a typical deep learning program to perform well on more than one task severely limits application of the technology to specific tasks in rigidly controlled environments. It has been claimed that deep learning is untrustworthy because it can experience catastrophic forgetting. It might therefore be risky to use deep learning on any life-or-death application, such as a medical one. In his new book Conscious Mind, Resonant Brain: How Each Brain Makes a Mind, Professor Stephen Grossberg of Boston University describes an alternative model for both biological and artificial intelligence based on cognitive and neural research he calls Adaptive Resonance Theory (ART). ART uses supervised and unsupervised learning methods to solve such problems. Algorithms using the theory have been included in large-scale applications such as classifying sonar and radar signals, detecting sleep apnea, recommending movies, and computer-vision-based driver-assistance software. According to him ART is useful for understanding the brain but also can be applied to the design of intelligent systems that are capable of autonomously adapting to a changing world…read more.