Book recommendations 4
Oct 18th 2022
Two books (curiously, with very similar blue cover) to obtain a personal start straight-A learning!!
Professor James Stone, in the 202 pages book "Artificial Intelligence Engines. A tutorial Introduction to the Mathematics of Deep Learning" , introduces us a very practical (tutorial approach) to the main Machine Learning algorithms, what he call "AI engines":
Contents
- AANs,
- LANs,
- Perceptrons,
- Backpropagation Algorithm,
- Hopfield nets,
- Boltzmann Machines,
- Deep RBMs,
- Variational Autoencoders,
- Deep Backprop Networks,
- Reiforcement Learning
- Appendices: - Glossary, Mathematical Symbols, Vector and Matrix Tutorial, MLE, Bayes' Theorem
100% Python code of the book github link
Tip: A very common problem in GitHub is the unique default option to download "all the repository". But to download exactly the sub-folder needed, I use (and strongly recommend) the GitZip for GitHub chrome extension.
Amazon Affiliate link:
After review and practice this previous short book, we are ready for the wonderful approach proposed by Professors Brunton and Kutz in their 472 pages book "Data Driven Science and Engineering. Machine Learning, Dynamic Systems and Control" . In this site: databookuw.com all the videos associated to each chapter, as well the MATLAB© and Python code, can be accessed.
Contents
- Common Optimization Techniques, Equations, Symbols, and Acronyms
- Part I - Dimensionality Reduction and Transforms
- Singular Value Decomposition (SVD)
- Fourier and Wavelet Transforms
- Sparsity and Compressed Sensing
- Part II - Machine Learning and Data Analysis
- Regression and Model Selection
- Clustering and Classification
- Neural Networks and Deep Learning
- Part III - Dynamics and Control
- Data-Driven Dynamical Systems
- Linear Control Theory
- Balanced Models for Control
- Data-Driven Control
- Part IV - Reduced Order Models
- Reduced Order Models (ROMs)
- Interpolation for Parametric ROMs
- Glossary
Thanks to free access obtained in Cambridge.org site, here is the SVD section:
Singular Value Decomposition (SVD)
Amazon Affiliate link to first edition (the one I have):
And here the Amazon Affiliate link to the second edition (july 2022!):
This second edition add new chapters on reinforcement learning and physics-informed machine learning and include Python, MATLAB©, Julia an R codes. The book homepage is the same of the first edition.
Please note that this two 2019 book, and the 2022 second edition of the second, not include Transformers, Attention or Stable Diffusion Models.
That is simply the expected delay of books in containing recent advances compared to papers.
From Hypotenuse AI, an example of a really big text-to-image model, with a typical result:
