AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Jordan Edwards: ML Engineering and DevOps on AzureML
Machine Learning Street Talk (MLST)
Deep Learning Models
Given sufficient testing, we would be able to infer that the model would run in production as expected. Deep ning is a bit like a hash table. Given a sufficiently des sampling of the impet space, there is some interpolation. We can't verbalize how we know things. An aeroplane pilot cannot tell you how he fli how he flies the plane. What we do is we do testing. And human intelligence has much broader generalization so less testing is needed.
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