The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Trends in Machine Learning & Deep Learning with Zack Lipton - #334
Dec 30, 2019
In this engaging discussion, Zack Lipton, a Professor at CMU with expertise in machine learning, explores key advances from 2019 in the field. He delves into the evolution of deep learning, noting the impact of models like BERT and challenges related to distribution shifts. Lipton also discusses innovative approaches in causal inference and fairness, advocating for continued research on model robustness. Lastly, he shares predictions about commodification in AI and the need for inclusive participation in the future landscape of machine learning.
AI Snips
Chapters
Transcript
Episode notes
Deep Learning's Trajectory
- Deep learning's rapid advancements have led to much low-hanging fruit in research.
- Now, researchers face limitations, prompting a shift towards more ambitious problems like causality and robustness.
Benchmark Overfitting
- Benchmark datasets, while useful for organizing research, raise concerns about overfitting.
- Reck et al.'s work explores this by creating fresh holdout sets for CIFAR and ImageNet.
New Holdout Set Results
- Models evaluated on the new holdout sets performed worse but maintained their relative ranking.
- This suggests that benchmark chasing is less flawed than feared, but classifiers remain brittle to distribution shifts.