Skip to content

Deep Learning for Biology course materials / Higher School of Economics, 2019

Notifications You must be signed in to change notification settings

che-shr-cat/deep-learning-for-biology-hse-2019-course

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

62 Commits
 
 
 
 
 
 

Repository files navigation

Deep Learning for Biology course materials / HSE 2019

This is a repository of course materials for the Deep Learning for Biology course.

The course is taught Fall 2019 at Higher School of Economics (Moscow), Faculty of Computer Science, Master’s Programme 'Data Analysis in Biology and Medicine'.

The contents

  • Course slides
  • Course Jupyter notebooks (using Tensorflow 2.0). Later in the course we switched to Colab notebooks. You can download them if you want.

Syllabus

(10/09/2019) 1. Artificial Intelligence: Current state and Overview

Topics:

  • Short history
  • Current results in Deep Learning
  • Images and Video
  • Speech and Sound
  • Text and Language
  • Robotic control
  • ML for systems
  • Problems with DL
  • Other approaches to AI
  • Knowledge and Representation
  • Symbolic approaches
  • Evolutionary computations and Swarm intelligence
  • Hardware

Slides:

Video:

(17/09/2019) 2. Introduction to Neural Networks

Topics:

  • Intro into NN: neuron, neural network, backpropagation,
  • Feed-forward NNs (FNN)
  • Autoencoders (AE)

Slides:

Video:

  • part 1 (including the last topic from previous lecture, the Hardware)
  • part 2

(24/09/2019) 3. Tensorflow 2/Keras practice

Code:

Video:

(01/10/2019) 4. Convolutional NNs (CNN) and Image processing

Topics:

  • What is CNN

Code:

Slides:

Video:

  • part 1
  • other parts are missing :(

(08/10/2019) 5. Real-life modern CNNs

Topics:

  • Activations, Regularization, Augmentation, Optimization etc
  • Models: LeNet, AlexNet, VGG, GoogLeNet, Inception, ResNet, DenseNet, XCeption, NASNet

Slides:

Video:

(15/10/2019) Journal Club #1

Video:

(29/10/2019) Journal Club #2

Video:

(05/11/2019) 6. Guest Lecture: Artur Kadurin, GANs

Slides:

Video:

(12/11/2019) 7. Transfer Learning

Topics:

  • Theory of Transfer Learning

Code:

Slides:

Video:

(12/11/2019) 8. Advanced CNNs

Topics:

  • 1D, 3D, dilated convolutions
  • Detection: R-CNN, Fast R-CNN, Faster R-CNN, YOLO
  • Fully-convolutional CNNs (FCNs)
  • Deconvolutional networks (Transposed convolution)
  • Generative Adversarial Networks (GANs)
  • Style Transfer

Code:

Slides:

Video:

(19/11/2019) 9. Recurrent NNs (RNNs)

Topics:

  • RNN basics, Backpropagation through time
  • Long short-term memory (LSTM)

Code:

Slides:

Video:

(26/11/2019) 10. Working with texts using RNNs

Topics:

  • Advanced RNNs: Bidirectional RNNs, Multidimensional RNNs
  • Working with texts: vectorizing, one-hot encoding, word embeddings, word2vec, BPE etc

Code:

  • Building text classifiers (LSTM, Deep LSTM, Bidirectional LSTM, 1D-CNN, CNN+LSTM)

Slides:

Video:

(03/12/2019) Journal Club #3

Video:

(10/12/2019) 11. Sequence Learning (seq2seq)

Topics:

  • Multimodal Learning
  • Seq2seq
  • Encoder-Decoder
  • Beam search
  • Attention mechanisms, Visualizing attention, Hard and Soft attention, Self-Attention
  • Augmented RNNs
  • Connectionist Temporal Classification (CTC)
  • Non-RNN Sequence Learning, problems with RNNs
  • Convolutional Sequence Learning

Slides:

Video:

(17/12/2019) 12. Transformers

Topics:

  • Self-Attention Neural Networks (SAN): Transformer Architecture
  • Transformer: The next steps (Image Transformer, Universal Transformer, Transformer-XL)
  • BERT & Co (RoBERTa, XLNet, ALBERT, etc), GPT-2, etc

Slides:

Code:

Video:

--- Need to be updated for TF 2.0 and other libraries ---

About

Deep Learning for Biology course materials / Higher School of Economics, 2019

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published