Published Jul 5, 2021
Vector Quantization for NN Compression with Julieta Martinez - #498
Julieta Martinez delves into neural network compression and large-scale visual search, focusing on innovative techniques like vector quantization and its role in enhancing efficiency. She also covers multitask learning's impact on systems, advocating for streamlined designs that manage extensive datasets effectively.

Topics covered
Popular Clips
Episode Highlights
Related Episodes


Advances in Neural Compression with Auke Wiggers - #570
Answers 383 questions

Probabilistic Numeric CNNs with Roberto Bondesan - #482
Answers 383 questions

Deep Learning for Automatic Basketball Video Production with Julian Quiroga - #389
Answers 383 questions

Real-Time Machine Learning in the Database with Nikita Shamgunov - #84
Answers 383 questions

Multi-Device, Multi-Use-Case Optimization with Jeff Gehlhaar - #587
Answers 383 questions

Gen AI at the Edge: Qualcomm AI Research at CVPR 2024 with Fatih Porikli - 688
Answers 383 questions

The Case for Hardware-ML Model Co-design with Diana Marculescu - #391
Answers 383 questions

Deep Neural Nets for Visual Recognition with Matt Zeiler - #22
Answers 383 questions

Rethinking Model Size: Train Large, Then Compress with Joseph Gonzalez - #378
Answers 383 questions

Cross-Device AI Acceleration, Compilation & Execution with Jeff Gehlhaar - #500
Answers 383 questions

Embedded Deep Learning at Deep Vision with Siddha Ganju - #95
Answers 383 questions

Quantum Machine Learning: The Next Frontier? - With Iordanis Kerenidis - #397
Answers 383 questions

Training Data for Computer Vision at Figure Eight with Qazaleh Mirsharif - #144
Answers 383 questions













