This Repository contains files and lecture slides from icme 2020 summer workshops and covered a wide range of topics from machine learning to HCP. Some documents are publicly available from instructors' websites (copyright notice).
- Workshop #0: Stat
- Workshop #1: Py
- Workshop #2: ML
- Workshop #3: DL
- Workshop #4: HCP
- Session 1
- Descriptive statistics for exploring data, especially visualization
- Sampling, studies and experiments
- Session 2
- Probability: basic rules, conditional probability, Bayes' rule
- Sampling distributions and the central limit theorem
- Session 3
- Regression
- Confidence intervals and the bootstrap principle
- Session 4
- Tests of significance, multiple comparisons and reproducibility
Here is an additional resource:
- Statistics Visualizations - Seeing Theory
- Session 1 Introduction
- Overview of Machine Learning
- Session 2 Unsupervised Learning
- Clustering (K-means, Hierarchical Clustering)
- Dimensionality Reduction (PCA, ICA, MDS, SOM, tSNE)
- Imputation
- Session 3
- Supervised Learning: Principles
- Cross-validation
- Regularization and Sparsity (lasso, ridge regression, elastic net)
- Supervised Learning: Principles
- Session 4
- Supervised Learning: Methods
- Classification and Regression Trees
- Ensembles
- Neural
- Supervised Learning: Methods
Reference books (see reference folder):
- An Introduction to Statistical Learning with Applications in R by G. James, D. Witten, T. Hastie, and R. Tibshirani - Free online book
- The Elements of Statistical Learning by T. Hastie, R. Tibshirani, and J. Friedman - Free online book
- Session 1
- Introduction
- Current state of the art in deep learning
- Math review
- Architecture of multi-layer neural networks
- Session 2
- Loss functions
- The backpropgation algorithm
- The gradient descent algorithm
- Over-fitting and Under-fitting
- Session 3
- Convolutional Neural Networks
- Recurrent Neural Networks
- Other Architectures
- Deep Learning Libraries
- Hands-on coding Session - Tensorflow
- Session 4
- Hands-on coding Session - Keras
- Hands-on coding Session - Transfer Learning
- Failures of deep learning
Here are some additional resources for various topics:
- Books
- Neural Networks and Deep Learning by Michael Nielsen - Free online book
- Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
- Visualizations
- Neural Network Playground - A playground for dense neural networks
- Gan Lab - A playground for GANs
- Initializing neural networks - Visual tutorial on initialization in deep learning
- Parameter optimization in neural networks - Visual tutorial on optimization in deep learning
- Stanford Courses
- Interesting talks on advanced topics
- Ben Recht - Training on test set and other heresies
- Aleksander Madry - A new perspective on Adversarial Perturbations
- Session 1: Algorithms
- Session 2: Shared Memory
- Session 3: Distributed Memory
- Session 4: Spark