Главная
Study mode:
on
1
​ - Introduction
2
​ - Course logistics
3
​ - Upcoming hot topics and guest lectures
4
​ - Deep learning and expressivity of NNs
5
​ - Generalization of deep models
6
- Neural network failure modes
7
- Uncertainty in deep learning
8
​ - Adversarial attacks
9
- Algorithmic bias
10
​ - Limitations summary
11
​ - Structure in DL
12
- Learning on graphs
13
- Learning on 3D pointclouds
14
​ - Automated Machine Learning AutoML
15
- Conclusion
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the limitations and new frontiers of deep learning in this comprehensive lecture from MIT's Introduction to Deep Learning course. Delve into topics such as the expressivity and generalization of neural networks, failure modes, uncertainty in deep learning, and adversarial attacks. Examine the challenges of algorithmic bias and discover emerging areas like learning on graphs and 3D point clouds. Gain insights into Automated Machine Learning (AutoML) and its potential impact on the field. Enhance your understanding of deep learning's current limitations and exciting future directions through this in-depth presentation by lecturer Ava Soleimany.

Deep Learning New Frontiers

Alexander Amini
Add to list
0:00 / 0:00