Deep learning godfathers Bengio, Hinton and LeCun say the field can fix its flaws
Artificial Intelligence conference held in Manhattan, where Yoshua Bengio, Geoffrey Hinton, and Yann LeCun took the stage to present a united front about how deep learning can move past obstacles like adversarial examples.
Co-conspirators in the revival in the field of “deep learning,” are Yoshua Bengio of Canada’s MILA institute, Geoffrey Hinton of the University of Toronto, and Yann LeCun of Facebook.
The three “Godfathers” of deep learning were in 34th annual conference of the Association for the Advancement of Artificial Intelligence, were being honored for having received last year’s Turing Award for lifetime achievements in computing.
Everyone who has attended conference acknowledged various shortcomings in deep learning, things such as “adversarial examples, and confident that the tools of deep learning will fix deep learning and lead to more advanced capabilities.
All the three have shared an Idea is that the solution is a form of machine learning called “self-supervised,” where something in data is deliberately “masked,” and the computer has to guess its identity.
Hinton named as capsule networks, which are like convolutional neural networks widely used in AI, LeCun said that, Self-supervised is training a model to fill in the blanks.
However masking information and then guessing it is made possible by a breakthrough in 2017 called the “Transformer,” made by Google scientists.
