Description
Book SynopsisAll engineers and applied scientists will need to harness the power of machine learning to solve the highly complex and data intensive problems now emerging. This text teaches state-of-the-art machine learning technologies to students and practicing engineers from the traditionally “analog” disciplines—mechanical, aerospace, chemical, nuclear, and civil. Dr. McClarren examines these technologies from an engineering perspective and illustrates their specific value to engineers by presenting concrete examples based on physical systems. The book proceeds from basic learning models to deep neural networks, gradually increasing readers’ ability to apply modern machine learning techniques to their current work and to prepare them for future, as yet unknown, problems. Rather than taking a black box approach, the author teaches a broad range of techniques while conveying the kinds of problems best addressed by each. Examples and case studies in controls, dynamics, heat transfer, and other engineering applications are implemented in Python and the libraries scikit-learn and tensorflow, demonstrating how readers can apply the most up-to-date methods to their own problems. The book equally benefits undergraduate engineering students who wish to acquire the skills required by future employers, and practicing engineers who wish to expand and update their problem-solving toolkit.
Table of ContentsPart I Fundamentals
1.0 Introduction
1.1. Where machine learning can help engineers
1.2. Where machine learning
cannot help engineers
1.3. Machine learning to correct idealized models
2. The Landscape of machine learning
2.1. Supervised learning
2.1.1. Regression
2.1.2. Classification
2.1.3. Time series
2.1.4. Reinforcement
2.2. Unsupervised Learning
2.3. Optimization
2.4. Bayesian statistics
2.5. Cross-validation
3. Linear Models
3.1. Linear regression
3.2. Logistic regression
3.3. Regularized regression
3.4. Case Study: Determining physical laws using regularized regression
4. Tree-Based Models
4.1. Decision Trees
4.2. Random Forests
4.3. BART
4.4. Case Study: Modeling an experiment using random forest models
5. Clustering data
5.1. Singular value decomposition
5.2. Case Study: SVD to standardize several time series
5.3. K-means
5.4. K-nearest neighbors
5.5. t-SNE
5.6. Case Study: The reflectance spectrum of different foliage
Part II Deep Neural Networks
6. Feed-Forward Neural Networks
6.1. Neurons
6.2. Dropout
6.3. Backpropagation
6.4. Initialization
6.5. Regression
6.6. Classification
6.7. Case Study: The strength of concrete as a function of age and ingredients
7. Convolutional Neural Networks
7.1. Convolutions
7.2. Pooling
7.3. Residual networks
7.4. Case Study: Finding volcanoes on Venus
8. Recurrent neural networks for time series data
8.1. Basic Recurrent neural networks
8.2. Long-term, Short-Term memory
8.3. Attention networks
8.4. Case Study: Predicting future system performance
Part III Advanced Topics in Machine Learning
9. Unsupervised Learning with Neural Networks
9.1. Auto-encoders
9.2. Boltzmann machines
9.3. Case study: Optimization using Inverse models
10. Reinforcement learning
10.1. Case study: controlling a mechanical gantry
11. Transfer learning
11.1. Case study: Transfer learning a simulation emulator for experimental measurements
Part IV Appendices
A. SciKit-Learn
B. Tensorflow
