DiscoverThe TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386
Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386

Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386

Update: 2020-06-251
Share

Description

We continue our CVPR coverage with today’s guest, Pavan Turaga, Associate Professor at Arizona State University, with dual appointments as the Director of the Geometric Media Lab, and Interim Director of the School of Arts, Media, and Engineering.

Pavan gave a keynote presentation at the Differential Geometry in CV and ML Workshop, speaking on Revisiting Invariants with Geometry and Deep Learning. In our conversation, we go in-depth on Pavan’s research integrating physics-based principles into computer vision. We also discuss the context of the term “invariant,” and the role of architectural, loss function, and data constraints on models. Pavan also contextualizes this work in relation to Hinton’s similar Capsule Network research.

Check out the complete show notes for this episode at twimlai.com/talk/386.

Comments 
In Channel
loading
Download from Google Play
Download from App Store
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386

Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386

Sam Charrington