The amazing story of the first successful round-the-world balloon trip. Autobiographic, the authors share with us their historic adventure, from the pThe amazing story of the first successful round-the-world balloon trip. Autobiographic, the authors share with us their historic adventure, from the preparation of the Breitling Orbiter 3 project in Switzerland to their return as heroes in Egypt via their stressful journey across continents and oceans. We get to know Bertrand and Brian at a personal level as they describe their time in the tiny capsule, their relationships on board but also with their team and families. We learn that their success was a combination of perseverance, technology, team expertise (e.g. the meteo guys) and sheer luck!
There was a nice touch of stoicism all along, about the importance of living in the Present (instead of being depressed by the Past and anxious of the Future), the purpose of a fulfilling life in a sustainable world, and accept that one cannot control the elements. The balloon makes the perfect metaphor for Life in that context: "In life you have the same kind of storms that can destroy you when you are ballooning and you are anxious about the future. There are moments when you have no wind and you are depressed by your stagnation; at other moments, everything seems so easy and smooth that you wonder why other people find life (or ballooning) so difficult [...] Life is a huge and difficult adventure because you are facing the unknown..." (p. 430).
It was nice also to read about the attempts by other stars such as Steve Fossett and Richard Branson, and about the illustrious Piccard family. I now want to read more about the father's and grand father's own achievements (back to the 1930s).
My rating is for the nice tutorial that this 'book' is. It is not per se a book but a collection of python notebooks. For it to be rated as a book, coMy rating is for the nice tutorial that this 'book' is. It is not per se a book but a collection of python notebooks. For it to be rated as a book, concepts should be developed in more detail and the writing style changed to not look like a series of blog posts.
So - as a tutorial on Bayesian methods - it was very instructive with a wide variety of examples presented, nice illustrations, and obviously all the python codes. I will for sure come back to it later to redo some of the Bayesian predictions myself....more
The book meanders through the world of Prediction, between forecasting of natural hazards to stock market prediction via games like baseball, poker anThe book meanders through the world of Prediction, between forecasting of natural hazards to stock market prediction via games like baseball, poker and chess. Overall an entertaining read.
On a personal level, since two of my articles are cited in there but only my PhD co-advisor was interviewed on those (part 5, refs. and ), I could clarify a few things: ref55. 'Bowman's technique, like Keilis-Bork's, was highly mathematically driven...' - It was my third paper at the end of my PhD and I had departed from the complexity theory of Dave Bowman by then, so it does not relate to the complexity view discussed in the present book nor to 'Bowman's technique'. ref.56 'a paper that [Bowman] published in 2006 also suggested that there was a particularly low risk of an earthquake... Just a year later..., a series of earthquakes hit exactly that area... It was devastating to Bowman's theory.' A good start for my academic career : ) I didn't feel the same as my co-author did. Having done the bulk of the analysis, I could see that jumps in the data had the potential to create signal where there was none (false positives) and hide potentially real signals (false negatives) - although it could well be that there was no signal at all. In complexity theory you were supposed to keep all events in the 'signal' (including the noise) which led me to start considering non-complexity approaches! As a compromise, I added all times series in an appendix for the reader to judge by himself. I continue working on seismicity physics and statistics to this day and I still believe that the process is more 'complicated' than 'complex'.
So when Silver writes 'If success in earthquake prediction has been almost nonexistent for millennia, the same was true for weather forecasting until about 40 years ago. Or it may be that as we develop our understanding of complexity theory-itself a very new branch of science-we may come to a more emphatic conclusion that earthquakes are not really predictable at all.', I answer: complexity is one theory, others might work better, future will tell! Obviously, as of now, no theory has demonstrated that earthquake prediction is possible or that it is impossible....more
It is "An Introduction to Statistical Learning: With Applications in R" but applied to Marketing research. A must-read for data scientists, as it intrIt is "An Introduction to Statistical Learning: With Applications in R" but applied to Marketing research. A must-read for data scientists, as it introduces (based on R codes) exploratory data analysis, data selection & transformation, hypothesis testing, things to verify or correct when applying linear regression, data complexity reduction, segmentation, etc & explains those tools and models based on marketing examples - I especially enjoyed the parts describing how synthetic data were simulated. A great complement to an Intro to SL, the present book is lighter on equations but heavier on business case studies....more
Obviously a go-to book for multilevel modelling but far from my favourite books on statistics. First, one should pass all the sections on probability Obviously a go-to book for multilevel modelling but far from my favourite books on statistics. First, one should pass all the sections on probability distributions and linear regression, since there is much better elsewhere on the same topic (and with R codes), such as 'An Introduction to Statistical Learning: With Applications in R'. One should then start reading this book at chapter 9. The causal inference view was very interesting and I especially enjoyed the simple R snippets on propensity scores. Yet, I remain unsatisfied, not really sure why. ...more
At the boundary between highly speculative science and science fiction, a book I would not have purchased had I not been stuck at an airport with littAt the boundary between highly speculative science and science fiction, a book I would not have purchased had I not been stuck at an airport with little other choice. In the style of Scientific American, should be read by teenagers to make them dream of a scientific career. Entertaining with nice pop-culture references, but nothing more....more
Excellent manual on statistical learning providing a simple Bayesian explanation for the most common statistical models. Some good examples: the authoExcellent manual on statistical learning providing a simple Bayesian explanation for the most common statistical models. Some good examples: the author explains the difference between least squares, ridge, lasso, etc. from different associations of distributions for the likelihood function and prior; or the MLE (high variance/possible overfitting) is the MAP estimate (high bias) with uniform prior, etc etc. Makes something that often looks like different cooking recipes into an ontology of clear related concepts. Includes also some useful summary tables (see eg Table 8.1 for a long list of models, classified as classification/regression, generative/discriminative, parametric/non-parametric). Very pedagogical. However, due to the length and sometimes depth of the maths, a book to read at different levels depending on what the reader is looking for. Also, I feel that the aspects presented in the second half of the book (trees, SVM, neural networks, Markov chains, etc., etc., etc.) are so varied, yet so technical, that books focused on those specific models may be preferred for some clarifications. ...more
Strong emphasis on the Bayesian viewpoint and heavy on equations. The coloured panels with the short bio of famous statisticians and other important sStrong emphasis on the Bayesian viewpoint and heavy on equations. The coloured panels with the short bio of famous statisticians and other important scientific figures were a welcomed addition to make the whole thing more digest. So overall a difficult read, certainly not the easiest to learn all the basics but an excellent manual for the researcher looking for something specific, especially if Bayesian related....more
What started like a very promising book ended up being a collection of snapshots on specific term comparisons using Google Ngram. It was interesting bWhat started like a very promising book ended up being a collection of snapshots on specific term comparisons using Google Ngram. It was interesting but a bit shallow as a consequence. This is unfortunate.
What I found fascinating was the part (in the first pages of the book) on the origin of irregular verbs. Anomalies in Zipf's law, they are the relics of the Proto-Indo-European language (6-12,000yrs old - Ablaut grammatical scheme such as ring rang rung, sing sang sung). They have survived into the Proto-Germanic language (500-250 BCE) but they are progressively being wiped out of our modern language. And one could make predictions as to the next irregular verbs to disappear! That's really the main example I will remember from that book. It was also fun, I must admit, to try to reproduce some of the book's plots on Google Ngram. ...more
Interesting methods/examples on how one can learn about people from Google search analytics (but also from Wikipedia, etc...). While it focuses on theInteresting methods/examples on how one can learn about people from Google search analytics (but also from Wikipedia, etc...). While it focuses on the author's research, we also learn about other researchers and companies' approaches to big data analytics, which was quite refreshing at times. I learned quite a few things, eg. that there is a natural equivalent to A/B testing (randomised controlled experiments) to real life decisions, by using so-called "regression discontinuity", or that one might do Freud symbolism hypothesis testing from a dream data App! However, minus one star for the unnecessary, occasional, creepy/gross parts....more
Indispensable complement to more technical data science books and, overall, a very easy and enjoyable read. A rich selection of business cases (from WIndispensable complement to more technical data science books and, overall, a very easy and enjoyable read. A rich selection of business cases (from Whisky list diversification at a liquor store, to stock price movement prediction based on news stories mining, via customer churn management). Thanks to very nice examples and illustrations, I, for example, now better understand (i) purity measure via entropy, and information gain for segmentation, (ii) the importance of expected value for classifier use framing, (iii) the relationship between IDF (inverse document frequency) and entropy, etc, etc....more
For the probability section, makes a fine (simpler) complement to Ross' 'A First Course in Probability'. Provides, as in Ross, many exercises but in aFor the probability section, makes a fine (simpler) complement to Ross' 'A First Course in Probability'. Provides, as in Ross, many exercises but in a different style. The rest of the book is about regression including an interesting chapter on time series....more
An impressive body of work on the life of famous (and less famous) mathematicians from antiquity to the early 20th century. We discover a melting pot An impressive body of work on the life of famous (and less famous) mathematicians from antiquity to the early 20th century. We discover a melting pot of lives, poor and rich, happy and sad, uneventful and rich of adventures. It is a pleasure to discover all those mathematicians from that personal-life angle and how mathematical discoveries are made within the socio-political sphere of the Time. It feels, however, that more than simple knowledge in mathematics is needed to truly enjoy this book and the importance of each mathematician's contribution. A brief overview of the evolution of Mathematics would have been welcome to help follow the flow....more
Disappointed. For some stoic reflection, better read Marcus Aurelius! And why is he always referring to wine??
Still, a few interesting quatrains:
#44 "Disappointed. For some stoic reflection, better read Marcus Aurelius! And why is he always referring to wine??
Still, a few interesting quatrains:
#44 "Alas! The book of youth is read so quickly, That fresh spring has yielded to the winter of life. Youth, that merry nightingale, alas! I knew neither when it came nor when it went away."
#93 "O heart! Imagine you have everything in the world, Imagine your pleasure garden is green; Then on that greenery, imagine you are like the dew, Appearing at night and disappearing in the morning."
An excellent introduction to statistical learning presenting the main algorithms for both regression and classification (linear regression, logistic rAn excellent introduction to statistical learning presenting the main algorithms for both regression and classification (linear regression, logistic regression, lasso, LDA, KNN, tree bagging and boosting, SVM, etc), as well as the important statistical tests (R^2, p-value, ROC, CV, concept of bias-variance tradeoff, etc...). Things are kept very simple with light-weight mathematics. The accompanying R labs help the reader consolidate his knowledge and get his hands dirty on real datasets. The exercises form an important complement but it is unfortunate that the answers are not given (one will manage to find most online though). It's important to always have exercises with answers: if one is able to answer all, he doesn't need to do the exercise in the first place. If one is stuck or just gets it wrong, only an access to the solution will make him progress. Note that the book focuses on classical methods and deep learning is not covered. Makes a nice complement to more technical ML manuals....more
Terrifying but potentially true. Everyone should read it to understand which are the worst possible scenarios for the (not-so-far) future of humanity.Terrifying but potentially true. Everyone should read it to understand which are the worst possible scenarios for the (not-so-far) future of humanity. Now we must minimax that game, minimize those maximum losses to avoid losing the Earth....more
For a 'first course in probability', it's quite heavy and complete. Be ready for some mild headaches on the way since the book is exercise-centric. BuFor a 'first course in probability', it's quite heavy and complete. Be ready for some mild headaches on the way since the book is exercise-centric. But it's worth it! If you want to learn virtually everything about combinations and random variables, this book is great. And I'm so glad to have learned about the concept of surprise and how, from a simple set of axioms, one can retrieve the entropy formula!! (check section 9.3). Another plus, despite the tremendous amount of exercises, all solutions are also provided (in like 80 pp. or so)....more
Targeted to the software engineer, the data scientist will also find some valuable information in this book. The first chapters are general enough thaTargeted to the software engineer, the data scientist will also find some valuable information in this book. The first chapters are general enough that the description of the interview process, difference between different tech companies, behavioural questions, etc, shall apply to both engineers and scientists. Then I really enjoyed the sections on math and logic puzzles and the advanced topics on math. Of course, the bulk of the book, on coding, will mainly interest the software engineer....more
Loading...
