d-t-n / hands-on-ml

Example code and solutions to the exercises in my O'Reilly book Hands-on Machine Learning with Scikit-Learn and TensorFlow

Hands-on ML

Example code and solutions to the exercises in my O'Reilly book Hands-on Machine Learning with Scikit-Learn and TensorFlow.

Book Content Index

Part I. The Fundamentals of Machine Learning

1. The Machine Learning Landscape

   • What Is Machine Learning?
   • Why Use Machine Learning?
   • Types of Machine Learning Systems
   • Supervised/Unsupervised Learning
   • Batch and Online Learning
   • Instance-Based Versus Model-Based Learning
   • Main Challenges of Machine Learning
   • Insufficient Quantity of Training Data
   • Nonrepresentative Training Data
   • Poor-Quality Data
   • Irrelevant Features
   • Overfitting the Training Data
   • Underfitting the Training Data
   • Stepping Back
   • Testing and Validating
   • Hyperparameter Tuning and Model Selection
   • Data Mismatch

   Notebook: - The Machine Learning Landscape

2. End-to-end Machine Learnng Project: * Look at the big picture - Get the data - Discover and visualize the data to gain insights - Prepare the data for Machine Learning algorithms - Select a model and train it - Fine-tune your model - Present your solution - Launch, monitor, and maintain your system

Notebook:
    - [End-to-end Machine Learnng Project](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/02-End_to_End_Machine_Learning_Project-.ipynb)

3. Classification * MNIST - Training a Binary Classifier - Performance Measures - Multiclass Classification - Error Analysis - Multilabel Classification - Multioutput Classification

Notebook:
    - [Classification](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/03-Classification.ipynb)

4. Training Models - Linear Regression - Gradient Descent - Polynomial Regression - Learning Curves - Regularized Linear Models - Logistic Regression

Notebook:
    - [Training Models](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/04-Training_Models.ipynb)

5. Support Vector Machines - Linear SVM Classification - Nonlinear SVM Classification - SVM Regression - Under the Hood

Notebook:
    - [Support Vector Machines](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/05-Support_Vector_Machines.ipynb)

6. Decision Trees - Training and Visualizing a Decision Tree - Making Predictions - Estimating Class Probabilities - The CART Training Algorithm - Computational Complexity - Gini Impurity or Entropy? - Regularization - Regression - Instability

Notebook:
    - [Decision Trees](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/06-Decision_Trees.ipynb)

7. Ensemble Learning and Random Forests - Voting Classifiers - Bagging and Pasting - Random Patches and Random Subspaces - Random Forests - Boosting - Stacking

Notebook:
    - [Ensemble Learning and Random Forests](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/07-Ensemble_Models.ipynb)

8. Dimensionality Reduction - The Curse of Dimensionality

Notebook:
    - [Dimensionality Reduction](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/08-Dimensionality_Reduction.ipynb)

9. Unsupervised Learning Techniques - Clustering - Gaussian Mixtures

Notebook:
    - [Unsupervised Learning Techniques](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/09-Unsupervised_Learning_Techniques.ipynb)

10. Introduction to Artificial Neural Networks with Keras - From Biological to Artificial Neurons - Implementing MLPs with Keras - Fine-Tuning Neural Network Hyperparameters

Notebook:
    - [Unsupervised Learning Techniques](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/10-Introduction_to_Artificial_Neural_Networks.ipynb)

11. Training Deep Neural Networks - The Vanishing/Exploding Gradients Problems - Reusing Pretrained Layers - Faster Optimizers - Avoiding Overfitting Through Regularization

Notebook:
    - [Training Deep Neural Networks](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/11-Training_Deep_Neural_Networks.ipynb)

12. Custom Models and Training with TensorFlow - A quick tour of TensorFlow - Using TensorFlow like Numpy - Customizing Models and Training Algorithms - TensorFlow Functions and Graphs

Notebook:
    - [Custom Models and Training with TensorFlow](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/12-Custom_Models_and_TF.ipynb)

13. Loading and Prepocessing Data with TensorFlow - The Data API - The TFRcord Format - Preprocessing the TF Transform - TensorFlow Dataset (TFDS) Project

Notebook:
    - [Loading and Prepocessing Data with TensorFlow](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/13-Loading_and_Prepocessing_Data_with_TF.ipynb)

14. Deep Computer Vision Using Convolutional Neural Networks - The Architecture of the Virtual Cortex - Convolutional Layers - Pooling Layers - CNN Arcitectures - Implementing a ResNet-34 CNN Using Keras - Using Pretrained Models from Keras - Pretrained Models for Transfer Learning - Classification and Localization - Object Detection - Semantic Segmentation

Notebook:
    - [Deep Computer Vision Using Convolutional Neural Networks](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/14_Deep_Computer_Vision_Using_Convolutional_Neural_Networks.ipynb)

15. Processing Sequences Using RNNs and CNNs - Recurrent Neurons and Layers - Training RNNs - Forecasting a Time Series - Handling Long Sequences

Notebook:
    - [Processing Sequences Using RNNs and CNNs](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/15_Processing_Sequences_Using_RNNs_and_CNNs.ipynb)

16. Natural Language Processing with RNNs and Attention - Generating Shakespearean Text Using a Character RNN - Sentiment Analysis - An Encoder–Decoder Network for Neural Machine Translation - Attention Mechanisms - Recent Innovations in Language Models

Notebook:
    - [Natural Language Processing with RNNs and Attention](https://nbviewer.jupyter.org/github/d-t-n/d-t-n/blob/master/16_Natural_Language_Processing_with_RNNs_and_Attention.ipynb)