...But they have existed for a very long time: since the early 90s for Q1 and since the early 80s for Q2. Now that the DL machinery works, and that so many people are working on both Qs, we have a shot at making real progress.
-
Indeed. I think
@ylecun's position is that to reach human-level AI/AGI, pipeline systems (such as@GaryMarcus's GQ3) will never suffice. In other words, training DL like systems to use logic/symbols/reasoning via gradient descent is likely to be more robust than two-stage system.
What’s the argument that it would actually be robust? No fair overrelying on data from image recognition to explain how such techniques would solve fundamentally different problems (language, common sense, everyday reasoning) that so far haven’t yielded to same approaches.
-
-
The ML community is working hard on the robustness question. We know that stochastic gradient descent sometimes confers robustness and other times fails miserably. We are exploring many avenues: causal models, adversarial training, improved models, etc.
-
Note of course difference between deep learning and ML; IMHO deep learning is useful, but just a subset of final ML toolbox. Ultimately ML will need to encompass many techniques (some not invented yet), and integrate them all to achieve robustness.
- 5 more replies
New conversation -
-
-
To apply machine learning to common sense and everyday reasoning, we of course need to collect data (or have our systems gain experience as embedded agents) on the "common sense" aspects of the world. This is also a major focus of research (and an upcoming
@darpa program) - 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.