We thank the author for his efforts to serve the scientific community, however, a novice reader may not be able to predict what kind of searching the author is referring to in the chapter’s title. Is this search related to information retrieval? Where we are supposed to search for some specific information with respect to some given request? Is he discussing a search engine? What we are searching for? After reading the first two pages, we discover that we are searching for some optimal solutions: local and global optimums related to some objective functions. Even if the problems discussed are combinatorial (NP-hard), the text should note that we are looking for approximate stochastic solutions, enabling us to recognize patterns, or to perform classification, learning, or information extraction from huge data sets.

While the author may have tried to provide an overview of what he meant by searching methods, it seems that he forgot to discuss clustering techniques and methods based on formal concept analysis (discussed in Ganter and Wille’s book [1]). Here, also, we try to extract pertinent information from data by searching for some optimal concepts. The author also may find the utilization of “optimal rectangles or concepts” for learning, discussed in Maddouri’s thesis [2], interesting. The lattice of concepts, which we can build from any high-dimensional space, is also a tentative way to find a regular structure from disorder.

The author presents a concrete explanation of stochastic search paradigms, using physical phenomena. He focuses on two stochastic search heuristics: simulated annealing (SA) and evolutionary algorithms (EA). He compares the basic schemes for the SA Metropolis algorithm and the standard evolutionary algorithms.

As a comment on the state-of-the-art, this chapter will be interesting for a general reader who is searching for knowledge about the philosophy of stochastic optimization techniques. However, we do not see what the author has really discovered, even if he is defending stochastic searching methods as a new and useful approach.

Most of the examples given are motivating, and have a clear objective. Unfortunately, the author does not convince the reader of the usefulness of the application of genetic algorithms to symbolic expressions. The genetic programming (GP) mutation, crossover, and recombination operators have been clearly applied to symbolic expressions (point mutation, permutation, collapse subtree mutation, expansion mutation, and duplication).

In conclusion, we think that this chapter is a valuable addition to its book. It is written in a good and interesting style, and the author does a good job of defending stochastic search methods as a new adaptive approach to solving combinatorial problems.This chapter is relatively easy to read, and very useful. It contains detailed descriptions of various well-known stochastic search methods.