AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Jordan Edwards: ML Engineering and DevOps on AzureML
Machine Learning Street Talk (MLST)
Onsombling for Neural Networks
Onsombling is a cheap way to take models that were trained on different data sets and sitch them together wel it's cheap from a training point of view, more expensive from an inference point of view. And unsampling is alsoa, knw, a big thing that we do internally, and we're just starting to scratch the surface on on model, on sampling. The solution that seems obvious to me for this problem would be like this knowledge distillation technique,. But i think we'll get there overtime. I just thinkthe space isn't quite advanced enough yet to do it. It's been essential for us to be able to actually use models in real time because you
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode