AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Learning Long-Time Dependencies with RNNs w/ Konstantin Rusch - #484
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is It a Hyper Barometer of Your Arinan Architecture?
Yer sowete te conel has many dimensions, rites, or basically, each dimension corresponds to one neuron in the recurrent iten state of the aran n. So typically, for for normal problems, use like a hundred 28 dimensions, or 256 dimensions. Would mean you have n our we are only talking for one layerr in ens right now. And coplet means that the information from one dimension can go also in the other dimension. That means, specically, the the hidden weight matrix we have is not sparse or has any structure. Its simple dance matrix, isit?
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