This is the repository for D-Lab’s Introduction to Deep Learning in R workshop.
Convey the basics of deep learning in R using keras on image datasets. Students are empowered with a general grasp of deep learning, example code that they can modify, a working computational environment, and resources for further study.
- Installation
- R and RStudio
- Keras and Tensorflow
- Helper packages
- What is “deep” learning?
- Understanding the dataset
- Dataset splitting: training, test, cross-validation
- Defining moving parts of a deep learning model
- Understanding a loss function, activation function, and metrics
- Performance evaluation
- Part 1-2
- MNIST 0-9 hand-written digit example
- Dogs or humans?
- Part 3-4
- Pre-trained models + fine-tuning
- X-ray classification: abdominal vs. chest classification
- Google Cloud Machine Learning
- D-Lab's Machine Learning in R introduction (4 hours)
- Or, comparable experience/training, assuming familiarity with:
- Basic R syntax
- statistical concepts such as mean and standard deviation
- Train/test splitting and cross-validation
- Dataset cleaning
- Overfitting / underfitting
- Hyperparameter customization
Please bring a laptop with the following:
- R version 3.4 or greater
- RStudio integrated development environment (IDE) is highly recommended but not required.
-
Websites
- RStudio Keras
- Supplementary notebook materials
-
Massive open online courses
- fast.ai - Practical Deep Learning for Coders
- Kaggle Deep Learning
- Google Machine Learning Crash Course
- See this sweet interactive learning rate tool
- Google seedbank examples
- DeepLearning.ai
-
Stanford
- CS 20 - Tensorflow for Deep Learning Research
- CS 230 - Deep Learning
- CS 231n - Neural Networks for Visual Recognition
- CS 224n - Natural Language Processing with Deep Learning
-
Berkeley
-
UToronto CSC 321 - Intro to Deep Learning
-
Videos
- J.J. Allaire talk at RStudioConf 2018
-
Books
- F. Chollet and J.J. Allaire - Deep Learning in R
- I. Goodfellow, Y. Bengio, A. Courville - www.deeplearningbook.org
- Zhang et al. - Dive into Deep Learning