Hands on Machine Learning With Scikit Learn and Tensorflow Published by Oreilly Review
Machine learning is apace condign an essential skill for data scientists and it has been applied in most, if non all aspects of science including Medical Physics.
Earlier reading this book, I had previously worked through a similar textbook chosen "Deep Learning with Python" by François Chollet which gave me the skills to build deep learning models but with only a passing familiarity of the concepts beneath the models I was building. François Chollet in fact gives a glowing review of his own regarding this book on the back cover.
This textbook, while not walking through examples in the aforementioned level of detail every bit Chollet, definitely filled in the theoretical knowledge I felt I was missing. Even so, someone with a good python groundwork can easily fill up in the missing code to brand their own total working examples. Having said that, the book as well includes a link to a GitHub repository where the reader tin can download many practise information sets and Jupyter notebooks with complete machine learning examples to supplement their learning.
This book includes footnotes at the bottom of each page with useful references to the original papers which the concepts currently existence discussed were kickoff described, or sometimes, just humorous observations.
The author often explains challenging concepts with useful analogies which I found very helpful. I example of this which I think deserves repeating here was an illustration of dropout regularisation. Employees are asked to flip a coin to run into if they should come into work. The visitor would be forced to adapt the arrangement to not rely on any single person to perform disquisitional tasks forcing the work to be spread across several people. If one person quit or is on sick get out it wouldn't make much of a departure. Eliminating the bus factor in a department. Something worth exploring especially in this age of COVID-nineteen peradventure?
The volume is divided into 2 parts, fundamentals of motorcar learning and neural networks/deep learning. At the finish of each chapter is a list of exercises for the reader to evaluate what they take learnt in that chapter. The appendix of the book contains solutions to each of those exercises.
Chapter 1 has a very broad overview of what auto learning is, how information technology all started and where the writer thinks it volition continue. This chapter contains a very nice list of examples where auto learning could be applied and which chapter to read to guide the reader in designing their own applications. This chapter also includes sections on the major challenges of machine learning such as: limited preparation data, poor information quality, overfitting and under plumbing equipment.
Chapter ii starts the reader on their own machine learning journey by giving a total worked example of a very typical regression style problem which includes steps such as: statistical analysis of your information, splitting the data into training and examination sets, visualisation, information cleaning, feature engineering and finally, builds some elementary regression models using python's Scikit-Learn module.
Chapter 3 continues this journeying past introducing classification tasks and guides the reader through the "hi world" of classification tasks, predicting digits from the "MNIST dataset".
Chapter 4 has an first-class discussion on the procedure of training diverse types of auto learning models and the various types of gradient descent optimisation algorithms.
Chapter five gives an overview of support vector machines, powerful and versatile motorcar learning models well suited for classification of circuitous small and medium size datasets.
Chapter six introduces Conclusion trees. This was an area of machine learning which I was not very familiar. This chapter helped me to empathize the usefulness of determination trees compared with other auto learning techniques and their limitations (e.g. their sensitivity to changes in coordinate organization). This affiliate introduces the concept of white box vs. black box motorcar learning models. Determination trees are 1 example of a white box model because the decisions choices are visibly apparent. These concepts are built upon in chapter 7 with a give-and-take of ensemble learning and random forest models. The author makes a good analogy betwixt posing a question to i expert or thousands of random people. The aggregated answer of the group of people may ofttimes exist better than the skillful. This is termed the "Wisdom of the crowd". This is a concept in ensemble learning and highlights the power of random forest models.
Chapter 8 has a discussion of dimensionality reduction techniques and the "Curse of dimensionality". This "curse" is very well explained, again, through simple analogies of the statistics of single points in multi-dimensional space. Principal component assay is well explained in this affiliate.
Chapter nine covers unsupervised learning techniques including the various types of information clustering techniques such equally One thousand-Means.
Affiliate 10 is the first of part II of the book and the beginning of the neural networks and deep learning discussion. This part of the volume focusses on artificial neural network applications with Keras (a pop and high level machine learning API in Python) and Tensorflow. This affiliate has a great discussion on the origins of artificial neural networks and their connection to biological neural networks. Although, the author is careful to emphasise that perhaps the analogy is however used too often and the relationship is not nearly as closely linked as near people call back. There is also a great explanation of how backpropagation is used to train an bogus neural network.
This chapter and then explains how to build some elementary Keras auto learning models and gives recommendations for best exercise. This affiliate actually highlights the subtleties of how Keras in particular works and what to look out for when training your model.
Affiliate eleven begins the section on deep learning applications. It starts by describing some of the common issues with deep learning models and how to approach them, such every bit: limited preparation data and reducing preparation time. In that location is a brief only intriguing give-and-take on the developments of optimising techniques in deep learning such every bit optimisers utilising 2d order partial derivatives which is an emerging field merely currently computationally infeasible due to memory requirements. There was a really interesting section on "Monte Carlo dropout" techniques which can boost existing model performance without having to re-train them. This is a technique particularly relevant to applications which are "risk sensitive" such as radiation oncology where it is useful to know how confident the model is in its prediction.
Chapter 12 and 13 introduces TensorFlow for building custom models and some of the tools information technology has available for data pre-processing.
Affiliate 14 covers computer vision applications with convolutional neural networks. It summarises some of the best performing convolutional neural networks to date such every bit AlexNet, VGGNet and ResNet and how to use transfer learning to build on these models for other applications. It also has some recommendations for open source image labelling tools for machine learning applications.
Chapter 15 and 16 discuss recurrent neural networks and their applications in tongue processing. There is a total worked case using recurrent neural networks to write new Shakespearean text from his existing works. This chapter was a lot of fun to read and work through the examples.
Chapter 17 focuses on auto encoders and generative adversarial networks (GANs). GANs have fascinated me ever since I first saw what they were capable of at the ACPSEM Machine Learning course in 2019. This chapter has some very nice worked examples on how to build your ain GANs.
Chapter 18 focusses on reinforcement learning such as teaching a machine to play games.
Chapter xix talks near deployment of your machine learning model, running machine learning models on embedded devices and how to speed up training and execution of your models with GPU acceleration.
With the addition of the resources provided in the GitHub repository, this book has everything you lot could want in a motorcar learning textbook. It provides an excellent starting point for someone who knows niggling or nothing about machine learning and wants to enter the field. It is also an excellent reference for someone who wants to build a specific application and needs a starting indicate to build on. This book's strength is its vast exploration of all aspects of machine learning while explaining the nuisances of machine learning (particularly using python, Scikit-Learn and Keras) in practice. The communication given in each chapter will aid you avoid some of the common pitfalls you might see on your own machine learning journey.
Author data
Affiliations
Respective author
Additional information
Publisher'southward Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Virtually this article
Cite this commodity
Douglass, M.J.J. Book Review: Hands-on Machine Learning with Scikit-Learn, Keras, and Tensorflow, 2nd edition past Aurélien Géron. Phys Eng Sci Med 43, 1135–1136 (2020). https://doi.org/10.1007/s13246-020-00913-z
-
Published:
-
Issue Date:
-
DOI : https://doi.org/x.1007/s13246-020-00913-z
Source: https://link.springer.com/article/10.1007/s13246-020-00913-z
0 Response to "Hands on Machine Learning With Scikit Learn and Tensorflow Published by Oreilly Review"
Postar um comentário