Deep Learning (The MIT Press Essential Knowledge series)

This book is by far the best introduction to deep learning I have read. It's very descriptive with useful diagrams and a gentle approach to the mathematics. If I'd started with this book two years ago when I set out to learn NN programming, it would have saved me a lot of time and internet searches. Highly recommended to anyone who wants to learn how to program neural networks.

Good introduction even for a non mathematician

I read the other introduction book by this author but have been disappointed with this book. The author assumes the reader has a good grasp of mathematics notation and concepts and references in the context of machine learning without offering further explanation of them. More examples would be useful to support especially when the first loan example is too basic to be built upon to illustrate the additional concepts

This is an entry in a series from the MIT Press that selects a small part of a topic (in this case, a subset of artificial intelligence) and gives it an 'essential knowledge' introduction. The problem is, there seems to be no consistency over the target audience of the series. I previously reviewed Virtual Reality in the same series and it kept things relatively simple and approachable to the general reader, even if it did overdo the hype. This book by John Kelleher starts gently, but by about half way through it has become a full-blown simplified textbook with far too much in-depth technical content. That's exactly what you don't want in a popular science title. What we get is plenty of detail of what deep learning-based systems are and how they work at the technical level, but there is practically nothing on how they fit with applications (unless you count playing games), which are described but not really explained, nor is there anything much on the problems that arise when deep learning is used for real world applications. There is a passing reference, admittedly to the difficulties of understanding how a deep learning AI system came to a decision and how this clashes with the EU's GDPR requirement for transparency and explanation, but if feels more like this is done to criticise the naivety of the legislation than the danger of using such systems. Similarly, I saw nothing about the dangers of deep learning systems using big data picking up on correlations that don't involve any causal link, nor does the book discuss the long tail problems that arise with inputs that are relatively uncommon and so are unlikely to turn up in the training data. Similarly we read nothing about the dangers of adversarial attacks, which can fool the systems into misinterpreting inputs with tiny changes, or the difficulties such systems have with real, messy environments as opposed to the rigid rules of a game. Overall, the book is both pitched wrong and doesn't cover the aspects that really matter to the public. It may well do fine as an introductory text for a computer science student, but that doesn't fit with the blurb on the back, which implies it is for public consumption.

A quality book about machine learning that exceeded my expectations. I congratulate the author, John D. Kelleher.

Contrairement à bien d'autres, l'auteur se donne pour objectif de bien faire comprendre son propos. Il y parvient à la faveur d'un réel effort pédagogique. Comme le précédent dans la même collection (Data science), l'ouvrage est clair et constitue un excellent panorama, accessible à un public de non-spécialistes. Sans technicité excessive, mais avec un cheminement suffisamment précis, il permet de comprendre les grandes lignes de la mise en oeuvre des principales méthodes présentées.

This is a good starting point for those interested in Deep learning . Also for all the technical buffs who have trouble explaining concepts to non-technical people in a simple way.

Scritto benissimo. Illustra in maniera divulgativa la storia dello sviluppo e soprattutto i principi di funzionamento del deep learning (altri libri si limitano invece a illustrarne le applicazioni). Un unico capitolo ha una quantità di matematica excessiva per una pubblicazione divulgativa ma l'autore stesso avvisa il lettore che può procedere oltre. È quindi un libro divulgativo ma rivolto a chi ha almeno una infarinatura scientifica. Consigliato.