Manolis Kellis
@manoliskellis1·24.9K subscribers·255 videos
MIT CompBio Lecture 12 - Deep Learning
Posted
October 20, 2018
Views
1,740
Likes
15
Engagement
0.86%
October 20, 2018
1,740
15
0.86%
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.
1:24:01Now PlayingMIT Computational Biology: Genomes, Networks, Evolution, Health
Prof. Manolis Kellis
Fall 2018
Lecture 12 - Networks I and Inference
1. Supervised Learning with Neural networks
- Perceptron, layers, activation units (sigmoid, softplus, ReLU)
- Learning: Gradient, Back-propagation, Rate, Dropout, Overfitting
2. Unsupervised learning with Deep belief networks
- Boltzmann machines, Restricted BMs (RBMs), Deep belief networks
- Learning: Energy, Gibbs Sampling, Simulated Annealing, Wake-sleep
3. Modern deep learning architectures
- Auto-encoders: Self-training, representation learning, RBM pre-training
- Convolutional neural networks: convolutional filters, pooling (sum/max)
- Recurrent neural networks: learning linear/temporal relationships
4. Deep learning in regulatory genomics
- Deciphering tissue-specific slicing code
- Deciphering regulatory grammars. DeepBind, DeepSea, Basset.
5. Three-dimensional structures: protein-DNA interactions, drug design
- Modern deep learning computing infrastructure
- Engines: TensorFlow, Theano, Torch, Caffe. Envs: Keras, Lasagene
Slides for Lecture 12:
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.
