GPU Accelerated Computation of VR Barcodes in Evaluating Deep Learning Models

GPU Accelerated Computation of VR Barcodes in Evaluating Deep Learning Models

Applied Algebraic Topology Network via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

GPU Accelerated Computation of VR Barcodes in Evaluating Deep Learning Models

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 GPU Acceleration after the End of Moore
  3. 3 Challenges to achieve GPU acceleration
  4. 4 GPUs in Deep Learning
  5. 5 The Simplex-wise Flag Filtration
  6. 6 Persistent homology: Birth and Death for of the C. elegans Dataset
  7. 7 Design Goals for High Performance
  8. 8 Efficient Persistent Pair Hashmap
  9. 9 Filtration Construction with Clearing is jus Filtering and Sorting Problem
  10. 10 Why do we need Ripser++
  11. 11 What is a Generative Adversarial Network
  12. 12 Deep learning model evaluation: using topology
  13. 13 MTop-Divergence Properties
  14. 14 Computational aspect of MTopDiv
  15. 15 Experiments with MTopDiv
  16. 16 Detecting distribution shifts
  17. 17 Computational considerations
  18. 18 Conclusion
  19. 19 VR barcodes of attention graphs as feature • Pretrained or finetuned BERT model with pretrained Key, Query Weight matrices. For each head compute the matrix of pairwise self attention

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.