AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
‘Neuroprosthesis for decoding speech in a paralyzed person with anarthria’ with David Moses and Jessie Liu
The Language Neuroscience Podcast
The Ensembling of Neural Networks
In the way that speech detection is continuous with a small amount of classes, classification here is discrete with a large number of classes. Both of us use recurrent models, and there are like, you know, other reasons why recurrent models are still good for classification. So I think one of the most interesting things perhaps Sean will disagree with me that I think about his model is the ensembling. He actually has 10 different models that he trains. And because his model didn't have to be, it wasn't meant to predict like every single time point, you can make this model a little more complex,. It can take a little more time to run.
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