5/11/2023 0 Comments Deep learning francois cholletIs how we will get to reasoning and abstraction, the fundamental weakness of current models. Models closer to general-purpose computer programs, built on top of far richer primitives than our current differentiable layers-this. I am sharing these predictions not because I expect them to be provenĬompletely right in the future, but because they are interesting and actionable in the present.Īt a high-level, the main directions in which I see promise are: So a lot of what I anticipate might fail to become reality. Given what we know of how deep nets work, of their limitations, and of the current state of the research landscape,Ĭan we predict where things are headed in the medium term? Here are some purely personal thoughts. You can read the first part here: The Limitations of Deep Learning. It is part of a series of two posts on the current limitations of deep learning, and its future. This post is adapted from Section 3 of Chapter 9 of my book, Deep Learning with Python (Manning Publications).
0 Comments
Leave a Reply. |