
Antonov and Piterbarg – 22/11/22
Quantcast – a Risk.net Cutting Edge podcast
Towards the Output Voice Requires Computational Efficiency
Using alternating least squares method, we basically fix all but one functions. And it's actually super efficient, basically. Compared to deep neural networks, it's about two orders of magnitude faster. So one takes 100 seconds, our stakes one second, and it's actually more accurate as well.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.