Published Jul 13, 2020
The Case for Hardware-ML Model Co-design with Diana Marculescu - #391
Diana Marculescu delves into the co-design of hardware and machine learning models with host Sam Charrington, revealing strategies for optimizing efficiency through predictive models, unified metrics, and integrating hardware constraints in neural architecture search to achieve power and memory savings without losing accuracy.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Multi-Device, Multi-Use-Case Optimization with Jeff Gehlhaar - #587
Answers 383 questions
Brain-Inspired Hardware and Algorithm Co-Design with Melika Payvand - #585
Answers 383 questions
Quantum Machine Learning: The Next Frontier? - With Iordanis Kerenidis - #397
Answers 383 questions
Vector Quantization for NN Compression with Julieta Martinez - #498
Answers 383 questions
Composing Graphical Models With Neural Networks, w/ David Duvenaud - #96
Answers 383 questions
Systems and Software for Machine Learning at Scale with Jeff Dean - #124
Answers 383 questions
Rethinking Model Size: Train Large, Then Compress with Joseph Gonzalez - #378
Answers 383 questions
Accelerating Deep Learning with Mixed Precision Arithmetic, w/ Greg Diamos - #97
Answers 383 questions
Real-Time ML Workflows at Capital One with Disha Singla - 606
Answers 383 questionsBuilding Blocks of Machine Learning at LEGO with Francesc Joan Riera - #533
Answers 383 questions
Deploying Edge and Embedded AI Systems with Heather Gorr - 655
Answers 383 questions
ML Models for Safety-Critical Systems with Lucas García - 705
Answers 383 questions
