-
NeurIPS has no free-loader problem: Most of the authors of submitted papers participate in reviewing.
- It is still unclear how to filter papers before the full review.
- Review quality (as measured by length) is not lower compared to smaller conferences.
From System 1 Deep Learning to System 2 Deep Learning In his keynote, Yoshua asks how far we are from human-level AI and whether it is enough to grow our datasets, model sizes, and computer speed. The keynote—inspired by
Thinking Fast and Slow—provides a roadmap on how to get from
System 1 (fast unconscious non-linguistic and habitual decision making/inference), which our models are good at, to
System 2 (slow, logical, sequential, conscious, linguistic, algorithmic, decision making).
Uniform convergence may be unable to explain generalisation in deep learning The Outstanding New Directions paper shows that many existing generalisation bounds fail to explain the generalisation behaviour of deep learning. In particular, these bounds increase with the training set size. They then provide a proof that shows that they
cannot explain generalisation even for a simple problem. Overall, while the paper does not provide a solution to generalisation in deep learning, it encourages the community to look in a different direction.
- Deconstructing the deep learning black box
- New approaches to deep learning (Bayesian, graph neural networks, convex optimisation)
- Neuroscience x Machine Learning
All talks from NeurIPS 2019 are available
here.
Another important event in terms of diversity and inclusion in AI was Khipu 2019, which took place in Montevideo in November. For an excellent summary, read the
8 main takeaways from tryo labs. In general, there are opportunities for everyone of us to strengthen the AI community and help others,
as described by Lila Ibrahim:
Sometimes that extra support is the difference between saying yes or saying no—between following a path in STEM, or doing something completely different. Whether it’s inspiring self-confidence, offering reassurance or providing a financial safety net, showing support and removing the barriers that prevent individuals achieving their full potential can have a powerful impact.