AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
How to build data science muscle memory, DeepChecks -- an open source ML testing suite - Philip Tannor - The Data Scientist Show #058
The Data Scientist Show
Do You Need to Train Your Neural Network First?
If the learning of the neural network doesn't converge well, then you shouldn't use them bedings in general. The method is that you only use like there's like a clear case in which it works. And would you say it probably works better when the data set is large enough and has a lot of features? Because if this is for kind of a simple actually boost problem, this might be, I don't know if it'd be like overfitting. But the PCA method was not like that far behind and that's like fantastic.
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