A pair of researchers recently developed a method for successfully conducting unsupervised machine learning that closely mimics how scientists believe the human brain works. These biologically-feasible algorithms could provide an alternate path forward for the field of AI. IBM researcher Dmitry Krotov and John J. Hopfield, inventor of the associative neural network, developed a set of algorithms that teach machines in the same loose, unfettered way humans learn. Their algorithms allow machines to learn in an unsupervised manner – without using the shortcuts (biologically-infeasible methods) that modern deep learning does. A lot of ancient AI research – conducted in the…

This story continues at The Next Web