Each node in an AI neural network is connected to many other such nodes, and the links can be statistically strengthened or weakened based on the data used to train the system. But, while they are inspired by the anatomy of the human brain, he writes, deep neural networks are brittle, inefficient and myopic when their performance is compared to that of an actual human brain. Deep neural networks are easy to fool with slight perturbations to the training inputs. This major difference between biological and artificial neural networks poses a profound challenge to the applicability of deep neural networks in areas such as clinical medicine and autonomous vehicles. Deep neural networks are data-hungry and inefficient, requiring huge amounts of training examples to learn distinctions that a human would find immediately obvious.

Source: Wall Street Journal February 07, 2020 20:56 UTC