Class link: https://frontendmasters.com/courses/practical-machine-learning/
Educational materials for Frontend Masters course "A Practical Guide to Deep Learning with TensorFlow 2.0 and Keras"
Prerequisite: Python
To use Jupyter Notebooks on your computer - please follow the installation instructions. Note: Anaconda installation is recommended if you are not familiar with other Python package management systems.
-
Install dependencies
pip install -r requirements.txt
-
Run jupyter notebook
jupyter notebook
- πββοΈ About myself
- About this course/workshop - quick demo & tools overview
- π¨ Whiteboard drawings
- π Jupyter Notebooks
- π¨π»βπ» Terminal commands (pip, jupyter -> !cmd, pyenv & conda)
- π» GitHub repos (for class, TFJS -> π₯ pose demo πΊ, books repos, TF/Keras demos)
- πΈ Websites (TF, TF-hub)
- π Books:
- "Deep Learning with Python" by François Chollet
- "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems" by AurΓ©lien GΓ©ron
- "Hands-On Neural Networks with TensorFlow 2.0" by Paolo Galeone
- (plot) What is the difference between Statistics / Machine Learning / Deep Learning / Artificial Intelligence? @matvelloso. Shoes size example. Information reduction.
- (plot) Compute + Algorithm + IO
- (plot) Why now, AI? Chronological retrospective.
- (plot) Hardware advances: SIMD, Tensor Cores, TPU, FPGA, Quantum Computing
- (plot) HW, compilers, TensorFlow and Keras -> computational graph, memory allocation
- Linear regression Notebook
- π΅π§ (plot) What is neuron? What is activation function?
- βπ» Handwritten digits (MNIST) recognized with fully connected neural network
- πΈ (plot) One-hot encoding
- π Information theory and representation: MNIST Principal Component Analysis
- π (plot) Fully connected vs. convolutional neural network
- π· (plot + Notebook) Convolutions, pooling, dropouts
- π (plot) Transfer learning and different topologies
- π¨ Style transfer
- π§ (Convolutional) Neural Network attention - ML explainability
- π€¬ Toxicity demo
- π (plot) How to represent text as numbers? Text vectorization: one-hot encoding, tokenization, word embeddings
- π IMDB movies review dataset prediction with hot-encoding in Keras
- π€― Word embeddings and Embedding Projector
- π Embedding vs hot-encoding and Fully Connected Neural Network for IMDB
- π Can LSTM guess the author?
- π (plot) Actors and environment
- Reinforcement learning
- (plot) Data - Training - Deployment aka MLOps or CI/CD for Data Scientists
- Quick recap what we learned so far