Deep Learning: John Kelleher **

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.

Paperback:

Kindle:

Using these links earns us commission at no cost to you

Review by Brian Clegg

Comments

The Art of Uncertainty - David Spiegelhalter *****

There's something odd about this chunky book on probability - the title doesn't mention the P word at all. This is because David Spiegelhalter (Professor Sir David to give him his full title) has what some mathematicians would consider a controversial viewpoint. As he puts it 'all probabilities are judgements expressing personal uncertainty.' He strongly (and convincingly) argues that while the mathematical approach to probability is about concrete, factual values, outside of the 'natural' probabilities behind quantum effects, almost all real world probability is a subjective experience, better described by more subjective terms like uncertainty, chance and luck. A classic way to distinguish between those taking the frequentist approach to probability and the Bayesian approach is their attitude to what the probability is of a fair coin coming up heads or tails after the coin has been tossed but before we have looked at it. The frequentist would say it's def

Everything is Predictable - Tom Chivers *****

There's a stereotype of computer users: Mac users are creative and cool, while PC users are businesslike and unimaginative. Less well-known is that the world of statistics has an equivalent division. Bayesians are the Mac users of the stats world, where frequentists are the PC people. This book sets out to show why Bayesians are not just cool, but also mostly right. Tom Chivers does an excellent job of giving us some historical background, then dives into two key aspects of the use of statistics. These are in science, where the standard approach is frequentist and Bayes only creeps into a few specific applications, such as the accuracy of medical tests, and in decision theory where Bayes is dominant. If this all sounds very dry and unexciting, it's quite the reverse. I admit, I love probability and statistics, and I am something of a closet Bayesian*), but Chivers' light and entertaining style means that what could have been the mathematical equivalent of debating angels on

Math for English Majors - Ben Orlin *****

Ben Orlin makes the interesting observation that the majority of people give up on understanding maths at some point, from fractions or algebra all the way through to tensors. At that stage they either give up entirely or operate the maths mechanically without understanding what they are doing. In this light-hearted take, Orlin does a great job of taking on mathematical processes a step at a time, in part making parallels with the structure of language. Many popular maths books shy away from the actual mathematical representations, going instead for verbal approximations. Orlin doesn't do this, but makes use of those linguistic similes and different ways of looking at the processes involved to help understanding. He also includes self-admittedly awful (but entertaining) drawings and stories from his experience as a long-time maths teacher. To make those parallels, Orlin refers to numbers as nouns, operations as verbs (though he points out that there are some flaws in this simile) a

Search This Blog