Two New Free Books on Machine Learning

Here are two great resources for machine learning and AI practitioners. Other recent free books can be found here. 

1. Free and Open Machine Learning Documentation

This book is all about applying machine learning solutions for real practical use cases. This means the core focus is on outlining how to use machine learning in a simple way so you can benefit of this powerful technology.

Machine learning is an exciting and powerful technology. The continuous use and growth of machine learning technology opens new opportunities. This great technology should available to use for everyone. This means that everyone should be able to learn, play and create great applications using machine learning technology.

The key focus of this publication in on Free and Open Machine learning technologies only. This to remove barriers for learning, playing and using machine learning technologies for real practical use cases for everyone.

Source for picture: see second book

Of course you can use or switch to a large commercial tech giant cloud company to deploy your machine learning driven application in production. However besides vendor lockin, crucial aspects like safety, privacy and security for machine learning application can only be realized when using fully transparent Free and Open technology.

By using outlining an open architecture, FOSS software and open datasets this publication outlines how machine learning technology can be available and usable for everyone. So without barriers. Since the majority of humans are not a graduated mathematician, we skip deep mathematical concepts of machine learning algorithms in this publication. Books with lots of mathematical background information on how machine learning works are available for more than 70 years. There are plenty excellent free and open publications available if you want to learn in depth the inner working of mathematical algorithms powering nowadays machine learning applications. In the learning resources section of this publication you can find some very good references. All available under a creative commons license (cc-by).

This publication has a core focus on how machine learning can be used. This is done by describing:

• Key machine learning concepts. The focus is on concepts that are needed in order to use solid FOSS machine learning frameworks and datasets when creating a machine learning powered application.
• An open reference architecture for creating and maintaining your machine learning application.
• Important open Solution Building Blocks (FOSS based) which you can use to create your machine learning application as fast as possible. Applying machine learning should be as easy and simple as possible. Only when barriers for using this technology are lowered many more great applications will be developed for the benefit for everyone.
• Key quality aspects for engineering and maintaining your machine learning driven application.
• Important safety, privacy and security aspects to prevent disasters
• Ethical issues (like bias) and how to handle this in a transparent way.

This book is created to give you a head start to use and apply Open Source machine learning technologies to solve problems. Without any strings attached, so the focus is on using open transparent technologies only!

The book features a large catalog of open ML software: see below an extract from the table of content:

You can access this 83-page book, here.  The current version at the time of this writing is Release 3, date January 20, 2020.

2. ML and DL frameworks and libraries for large-scale data mining: a survey

Published in June 2019 in the Artificial Intelligence Review journal. Available here. 

The combined impact of new computing resources and techniques with an increasing avalanche of large datasets, is transforming many research areas and may lead to technological breakthroughs that can be used by billions of people. In the recent years, Machine Learning and especially its subfield Deep Learning have seen impressive advances. Techniques developed within these two fields are now able to analyze and learn from huge amounts of real world examples in a disparate formats. While the number of Machine Learning algorithms is extensive and growing, their implementations through frameworks and libraries is also extensive and growing too. The software development in this field is fast paced with a large number of open-source software coming from the academy, industry, start-ups or wider open-source communities. This survey presents a recent time-slide comprehensive overview with comparisons as well as trends in development and usage of cutting-edge Artificial Intelligence software. It also provides an overview of massive parallelism support that is capable of scaling computation effectively and efficiently in the era of Big Data.

This work is supported by the “Designing and Enabling E-infrastructures for intensive Processing in a Hybrid DataCloud” (DEEP-Hybrid-DataCloud) project that has received funding from the European Union’s Horizon 2020 Research and Innovation Programme.