Manolis Kellis
@manoliskellis1·24.9K subscribers·255 videos
MIT Deep Learning Genomics - Lecture 4 - Recurrent Neural Networks (Spring 2020)
Posted
February 13, 2020
Views
2,313
Likes
38
Comments
4
Engagement
February 13, 2020
2,313
38
4
1.82%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
See what was published immediately before and after this episode.
1:13:57Now PlayingMIT 6.874 Lecture 4. Spring 2020
Course website
Lecture slides
Slides credit: Geoffrey Hinton, Ian Goodfellow, David Gifford, Manolis Kellis, 6.S191 (Ava Soleimany, Alex Amini)
Recurrent Neural Networks (RNNs) outline:
1. How do you read/listen/understand/write? Can machines do that?
– Context matters: characters, words, letters, sounds, completion, multi-modal
– Predicting next word/image: from unsupervised learning to supervised learning
2. Encoding temporal context: Hidden Markov Models (HMMs), RNNs
– Primitives: hidden state, memory of previous experiences, limitations of HMMs
– RNN architectures,unrolling,back-propagation-through-time(BPTT),param reuse
3. Vanishing gradients, Long-Short-Term Memory (LSTM), initialization
– Key idea: gated input/output/memory nodes, model choose to forget/remember
– Example: online character recognition with LSTM recurrent neural network
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
