This may result in conflicting information, uncertainty, and alternative facts. Our state of mind is based on experiences and what other people tell us. #102: Leolani: a Reference Machine with a Theory of Mind for Social Communication Piek Vossen, Selene Baez, Lenka Bajcetić, Bram Kraaijeveld In practice, deep nets have produced extremely exciting results in vision and speech, though other tasks may be more challenging for deep nets. They don't do the impossible (solve the halting problem), and they probably aren't great at many tasks such as sorting large vectors and multiplying large matrices. Deep nets are probably not the solution to all the world's problems.
Section 5 will propose an organizing framework for deep nets. While their arguments may sound negative, I believe there is a more constructive way to think about their efforts they were both attempting to organize computational tasks into larger frameworks such as what is now known as the Chomsky Hierarchy and algorithmic complexity. Many of their objections are being ignored and forgotten (perhaps for good reasons, and perhaps not). Minsky's Perceptrons was a reaction to neural nets and Chomsky's Syntactic Structures was a reaction to ngram language models. When Minsky and Chomsky were at Harvard in the 1950s, they started out their careers questioning a number of machine learning methods that have since regained popularity. TSD 2018 Paper Abstracts #101: Minsky, Chomsky & Deep Nets Kenneth Ward Church
0 kommentar(er)
