AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Stellar inference speed via AutoNAS
Practical AI: Machine Learning, Data Science, LLM
Is There a Better Architecture for Image Classification?
We have a collaboration with intel that we recently published in amelpurf last september or something like that, about a performance bisteot that we've made to image classification model resinent 50. It is very interesting to see that, first of all, it replaces some of the operations from dance convolution layers, deptwise and some other vincs of convolutional layers that are less memory bounded. Second thing that we can learn from that idea is that some layers are more important than others. So putting kind of most of the computation at the beginning of the network seems to have better accuracy preserving properties.
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