Machine Learning Street Talk (MLST) #036 - Max Welling: Quantum, Manifolds & Symmetries in ML
18 snips
Jan 3, 2021 
This conversation features Max Welling, a prominent Professor and VP of Technology at Qualcomm, known for his innovative work in geometric deep learning. He discusses the crucial role of domain knowledge in machine learning and how inductive biases impact model predictions. The dialogue also explores the fascinating intersection of quantum computing and AI, particularly the potential of quantum neural networks. Furthermore, Welling highlights the significance of symmetries in neural networks and their applications in real-world problems, including protein folding.
AI Snips
Chapters
Books
Transcript
Episode notes
Fashion in ML Research
- Machine learning research follows cycles of excitement around different topics.
- These "fashions" allow deep dives into promising tools, maximizing their potential before moving on.
Compute vs. Energy Efficiency
- Increased compute in machine learning models leads to better performance but higher energy consumption.
- Future AI development must prioritize energy efficiency.
Generative Models and Intelligence
- Generative models, simulating how the world creates data, are crucial for AI.
- This ability to generate, like humans do, seems key to true intelligence.
