Abstract-This paper presents a fundamental algorithm for parsing natural language sentences into dependency trees. Unlike phrase-structure (constituency) parsers, this algorithm operates one word at a time, attaching each word as soon as it can be attached, corresponding to properties claimed for the parser in the human brain. This paper develops, from first principles, several variations on a fundamental algorithm for parsing natural language into dependency trees. This is an exposition of an algorithm that has been known, in some form, since the 1960s but is not presented systematically in the extant literature. Unlike phrase-structure (constituency) parsers, this algorithm operates one word at a time, attaching each word as soon as it can be attached. There is good evidence that the parsing process used by the human mind has these properties [1].

Today's artificial intelligence (AI) can do some extraordinary things. Its functionality, though, has very little to do with the way in which a human brain works to achieve the same tasks. For AI to overcome its inherent limitations and advance to artificial general intelligence, we must recognize the differences between the brain and its artificial counterparts. With that in mind, this nine-part series examines the capabilities and limitations of biological neurons and how these relate to machine learning (ML). In the first two parts of this series, we examined how a neuron's slowness makes an ML approach to learning implausible in neurons, and how the fundamental algorithm of the perceptron differs from a biological neuron model involving spikes.

Robotic vision, the combination of robotics and computer vision, involves the application of computer algorithms to data acquired from sensors. The research community has developed a large body of such algorithms but for a newcomer to the field this can be quite daunting. For over 20 years the author has maintained two open-source MATLAB Toolboxes, one for robotics and one for vision. They provide implementations of many important algorithms and allow users to work with real problems, not just trivial examples. This book makes the fundamental algorithms of robotics, vision and control accessible to all.

This book generally does a good job of not assuming prior math / notation knowledge. The problem I have with most ai or game theory books is that they assume you have a math undergrad or grad degree. I come from an applied arts (design) background and this book was really helpful for getting my head around the basics of ai algorithms. Some of the explanations were lacking completeness and the author doesn't clearly tie the last two chapters to the rest of the book with concrete examples. There are some formatting issues and errors in the book.

This book claims to be an overview of artificial intelligence, but it's not; it's an overview of machine learning. It's true that machine learning is a hot topic within AI just now, but it's hardly taken over the field, nor has it rendered all other methods obsolete. But, if you just want an informal introduction to the basic forms of machine learning, it's short and easy to read. The rubber never quite meets the road, but if all you need is the basic concepts, it's not a bad start. It does, however, contain errors that really should have been caught prior to publication. In addition to the errors mentioned by another reviewer, the references to equations 10.2 through 10.4 are wrong, and the description of the logistic function shown in Figure 10.3 doesn't match the function shown.