What do you think?
Rate this book
Data Science – was ist das eigentlich?!: Algorithmen des maschinellen Lernens verständlich erklärt
Sie möchten endlich wissen, was sich hinter Schlagworten wie „Data Science“ und „Machine Learning“ eigentlich verbirgt – und was man alles damit anstellen kann? Auf allzu viel Mathematik würden Sie dabei aber gern verzichten? Dann sind Sie hier genau richtig: Dieses Buch bietet einen kompakten Einblick in die wichtigsten Schlüsselkonzepte der Datenwissenschaft und ihrer Algorithmen – und zwar ohne Sie mit mathematischen Formeln und Details zu belasten!
Der Fokus liegt – nach einer übergeordneten Einführung – auf Anwendungen des maschinellen Lernens zur Mustererkennung und Vorhersage von Ergebnissen: In jedem Kapitel wird ein Algorithmus erläutert und mit einem leicht verständlichen, realen Anwendungsbeispiel verknüpft. Die Kombination aus intuitiven Erklärungen und zahlreichen Abbildungen ermöglicht dabei ein grundlegendes Verständnis, das ohne mathematische Formelsprache auskommt. Abschließend werden auch die Grenzen und Nachteile der betrachteten Algorithmen explizit aufgezeigt.
Der Fokus liegt – nach einer übergeordneten Einführung – auf Anwendungen des maschinellen Lernens zur Mustererkennung und Vorhersage von Ergebnissen: In jedem Kapitel wird ein Algorithmus erläutert und mit einem leicht verständlichen, realen Anwendungsbeispiel verknüpft. Die Kombination aus intuitiven Erklärungen und zahlreichen Abbildungen ermöglicht dabei ein grundlegendes Verständnis, das ohne mathematische Formelsprache auskommt. Abschließend werden auch die Grenzen und Nachteile der betrachteten Algorithmen explizit aufgezeigt.
175 pages, Kindle Edition
Published October 24, 2018
1058 people are currently reading
1041 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 30 of 81 reviews
October 25, 2019
A fun intro into data science (a sneak peak, even) without much data or math or coding or techy stuff or ... well, anything that could be suspected to be difficult. So, no allergies are likely to plague the audience.
A lot of visual descriptions, quite a lot about the general principles of algorithms.
Nicely written, easy to understand for newbies; although I know a bunch of advanced wannabes who swear by it. :)
A tad too easy. But that's probably just me. Not the book.
A lot of visual descriptions, quite a lot about the general principles of algorithms.
Nicely written, easy to understand for newbies; although I know a bunch of advanced wannabes who swear by it. :)
A tad too easy. But that's probably just me. Not the book.
June 19, 2024
Попри декілька помилок (причому доволі грубих!) це ідеальна книга, щоб зорієнтуватися в нових методах аналізу даних. З одного боку, тут немає формул. З іншого боку, достатньо точно описано, як працює метод, і які результати дозволяє отримати.
Звісно, без формул зрозуміти метод та його обмеження складно. Але якщо ви орієнтуєтеся в матеріалі, то ця книга дозволяє систематизувати знання - і навіть дізнатися щось нове. А точніше - знати, що саме шукати, щоб знайти нове!
Звісно, без формул зрозуміти метод та його обмеження складно. Але якщо ви орієнтуєтеся в матеріалі, то ця книга дозволяє систематизувати знання - і навіть дізнатися щось нове. А точніше - знати, що саме шукати, щоб знайти нове!
September 13, 2023
First, the conclusion: if you have an afternoon to spare, read this book to become data literate.
Who I am: I work for an IT company as a project manager who works with developers, designers, writers, and product owners on a day-to-day basis. As part of my learning journey, I read this book in order to familiarize myself with the vocabulary and inner workings of data science.
I'm glad Numsense exists because most of the books on the market are written for developers - in other words, they are too technical. This books fills an important gap: if we want our world to prosper and our businesses to thrive, we need to democratize DS so as many people as possible know what it is and how to use it.
This book has three strengths:
1. It's an easy and insightful read.
A high school student probably can read it without much effort. However, that is not to say the book is simplistic. On the contrary, the authors did an excellent job of distilling DS concepts (e.g. k-Means, Principle Component Analysis etc) to their very essence - a genuine accomplishment!
2. It has tons of visuals that aid comprehension.
The authors included plenty of graphs, tables, and illustrations to explain DS concepts that are a feast for the eyes. Where words fail (and they rarely do), visuals come to the rescue.
3. It consists of many helpful examples.
DS (and AI, really) has no value if you don't put it into good use. The book is equally strong on theory AND practice. You'll get a good sense of how DS algorithms are actually applied in the real world.
All in all, highly recommended for anyone (not just those working for a tech company, like I do) interested in the art and science of data science - and my sincere thanks for Annalyn and Kenneth who made DS so accessible to many of us laymen!
Who I am: I work for an IT company as a project manager who works with developers, designers, writers, and product owners on a day-to-day basis. As part of my learning journey, I read this book in order to familiarize myself with the vocabulary and inner workings of data science.
I'm glad Numsense exists because most of the books on the market are written for developers - in other words, they are too technical. This books fills an important gap: if we want our world to prosper and our businesses to thrive, we need to democratize DS so as many people as possible know what it is and how to use it.
This book has three strengths:
1. It's an easy and insightful read.
A high school student probably can read it without much effort. However, that is not to say the book is simplistic. On the contrary, the authors did an excellent job of distilling DS concepts (e.g. k-Means, Principle Component Analysis etc) to their very essence - a genuine accomplishment!
2. It has tons of visuals that aid comprehension.
The authors included plenty of graphs, tables, and illustrations to explain DS concepts that are a feast for the eyes. Where words fail (and they rarely do), visuals come to the rescue.
3. It consists of many helpful examples.
DS (and AI, really) has no value if you don't put it into good use. The book is equally strong on theory AND practice. You'll get a good sense of how DS algorithms are actually applied in the real world.
All in all, highly recommended for anyone (not just those working for a tech company, like I do) interested in the art and science of data science - and my sincere thanks for Annalyn and Kenneth who made DS so accessible to many of us laymen!
July 21, 2017
Great Overview for the Uninitiated
I took the Coursera John Hopkins Data Science certification a few years ago. This book would have been great intro before starting that trek. I enjoyed the authors' simplicity and brevity. Highly recommended for dipping your toe into the data science data lake (or whatever moniker is being used today.)
I took the Coursera John Hopkins Data Science certification a few years ago. This book would have been great intro before starting that trek. I enjoyed the authors' simplicity and brevity. Highly recommended for dipping your toe into the data science data lake (or whatever moniker is being used today.)
April 13, 2019
Теперь я могу понимать, о чем говорят датасаентисты.
March 19, 2024
Book contents:
10% preparation & evaluation and 90% algos & limitations, explained in plain text and illustrations. It's an overview, detailed enough to get an idea of what's going on when using (not implementing) data science algorithms as you have to experiment with different algos; data science seems trial-and-error heavy (attributes selection, algorithms selection etc).
...compared to the "Data Science" book from the MIT Essential Knowledge series:
30% algos (wordy) and 70% extract, clean, and integrate data a.k.a. data plumbing ("80% of the time"), a data mining process model (CRISP-DM), ethics and regulations.
These 70% have no place in the Numsense book, so both books can be read in addition to each other (both introductions). There's overlap between the algos, but are explained in different ways.
10% preparation & evaluation and 90% algos & limitations, explained in plain text and illustrations. It's an overview, detailed enough to get an idea of what's going on when using (not implementing) data science algorithms as you have to experiment with different algos; data science seems trial-and-error heavy (attributes selection, algorithms selection etc).
...compared to the "Data Science" book from the MIT Essential Knowledge series:
30% algos (wordy) and 70% extract, clean, and integrate data a.k.a. data plumbing ("80% of the time"), a data mining process model (CRISP-DM), ethics and regulations.
These 70% have no place in the Numsense book, so both books can be read in addition to each other (both introductions). There's overlap between the algos, but are explained in different ways.
January 30, 2020
An excellent introduction to data science. Short, understandable, and concise. There is no math involved. But if you look into the material on the GitHub repository of the book, you will find all the details, including the R scripts and data files. So you can reproduce calculation and statistics used by the authors. Therefore for me, this small book is a fantastic resource for learning data science.
January 10, 2018
Great and simple overview of the most important machine learning models. This book is very useful if you have a fundamental understanding about machine learning, but feeling confused about what is what. The chapters can push you in the right direction and give you a good intuition. Given that, you will have a good grounding to start diving deeper into any of the models you like.
April 22, 2018
Numsense! Data Science for the Layman is a great little book. Not only could it be a fine introduction for someone with little if any knowledge of data science, but it also provides nice summaries of several different areas for those with familiarity. Five starts for doing what the title says.
March 9, 2018
A very good introductory level ML book
This is a very good introductory level machine learning book, especially for those without very strong math background. It tells the algorithms in a very clear and simple way. I will recommend this book for machine learning beginners.
This is a very good introductory level machine learning book, especially for those without very strong math background. It tells the algorithms in a very clear and simple way. I will recommend this book for machine learning beginners.
October 9, 2018
A good overview of all basic Data science algorithms. Nice book to revise your concepts. The examples are also spot on.
As mentioned in title, No math added so it does not explore the algos from mathematical standpoint. But still suffices its purpose.
As mentioned in title, No math added so it does not explore the algos from mathematical standpoint. But still suffices its purpose.
December 17, 2019
Appreciate the effort taken by the authors to write such a book. I can imagine the tough ask of making Data Science easy to understand to newbies. The author has done a commendable job to initiate the curiosity to the readers.
July 18, 2017
Best book about the Data Science for a layman. Clear and precise definitions, can be read with in few hours.
March 20, 2018
Good machine learning start book
Easy to read. It gives a good grasp of different machine learning algorithms. It explains complex techniques in a very comprehensive way.
Easy to read. It gives a good grasp of different machine learning algorithms. It explains complex techniques in a very comprehensive way.
July 20, 2022
i understood nothing
January 18, 2020
Such an AWESOME book to summarize data science concepts, written by a friend from high school. I needed a refresher on machine learning algorithms and this book is just PERFECT, I finished it in a few hours. As promised, no maths or any equations added.
February 24, 2025
Структура книги і приклади пояснень різних способів роботи з даними сподобалися, розумію, чому таких прикладів не може бути більше у ознайомчому виданні, але хотілося б, часом було складніше уявити, як це працює на практиці, але загалом інформації достатньо, щоб побачити, в чому переваги та складнощі роботи з даними
October 4, 2019
This broad brush introduction to data science without mathematics is okay as far as it goes. The lack of math does become a very limiting factor in being able to understand some of the concepts. Additionally, many of the the figures used to illustrate the ideas are dependent upon the use of colors, which makes them impossible to decipher on a standard gray-scale kindle. The authors also explain the use of black boxes that provide results without there being an explanation for how these specific results were generated. In other words, you have to wonder why we as a society are giving so much control and freedom to black boxes that are only "good enough" that is underpinning much of the AI applications being used around the world today, but that is a different subject for a different book. Overall, I'm not sure that data science without the math is worth the time.
September 15, 2019
Good but something is missing
Although the whole concept is keep it simple, sometimes it feels too light and that something is missing to connect the dots. Topics such as Neural Networks should be explained a bit deeper or removed at all.
Although the whole concept is keep it simple, sometimes it feels too light and that something is missing to connect the dots. Topics such as Neural Networks should be explained a bit deeper or removed at all.
September 8, 2019
Explanations about different algorithms and techniques for machine learning/data science were simplified so the readers can focus on how it can be used in a specific problem/project. Clearly, a book for beginners. I’m just expecting a bit more discussion on real-world applications than just one or two. Either way it’s a painless read especially for someone starting his/her interest in data science.
December 12, 2017
Pretty good gentle introduction to some data science terms and techniques. This is a good refresher or first introduction to some general ideas and high-level techniques. It doesn't weigh you down with the math. It explains the concepts using plain English.
At the time I read this, it was available as a book you could check out for free if you were an Amazon Prime member. I have no hesitation in recommending this if you can do that as well and you are interested in these concepts at all.
I read this on an E ink Kindle. Unfortunately, many of the figures use color and this was lost. It might be better to read this on your phone or tablet.
At the time I read this, it was available as a book you could check out for free if you were an Amazon Prime member. I have no hesitation in recommending this if you can do that as well and you are interested in these concepts at all.
I read this on an E ink Kindle. Unfortunately, many of the figures use color and this was lost. It might be better to read this on your phone or tablet.
April 25, 2018
Very hard to judge by the cover
I was first disappointed in the lack of maths. Even though it was in the title. Then there is actually some math, so at this point I felt the urge penalise. The book is actually very good, and entertaining. It is told to be used at Stamford on some early levels for data science. Delivers good instructions. I think I actually realised the difference between a random forest and neutral network. Time will tell when I get deeper in the field if this was actually understand. Book includes a dozen different methods explaining their strengths, and limitations.
I was first disappointed in the lack of maths. Even though it was in the title. Then there is actually some math, so at this point I felt the urge penalise. The book is actually very good, and entertaining. It is told to be used at Stamford on some early levels for data science. Delivers good instructions. I think I actually realised the difference between a random forest and neutral network. Time will tell when I get deeper in the field if this was actually understand. Book includes a dozen different methods explaining their strengths, and limitations.
October 7, 2018
A wonderful book that gives a bird's eve view of data science algorithms and concepts. A beginner like me found it excellent, clarifying concepts while not getting bogged down in mathematical details.
The book has apt illustrations/diagrams and examples that enables one to grasp the general idea.
Short and powerful.
The book has apt illustrations/diagrams and examples that enables one to grasp the general idea.
Short and powerful.
October 11, 2018
As it says on the tin. Easy to follow, even if you do not have great knowledge of statistics or data beforehand. The book amazingly avoids any dive into mathematics, while the examples are really helpful. It is also short, so you can easily finish it within ten days/two weeks without dedicating too much time on a daily basis.
June 7, 2019
Good introduction to Data Science
This is a short and sweet introduction to Data Science. I had tried understanding Data Science from experts with varying level of success, but this book does the job of explaining at a high level very well. The book still leaves a few questions in my mind unanswered, but overall it has done a good job.
This is a short and sweet introduction to Data Science. I had tried understanding Data Science from experts with varying level of success, but this book does the job of explaining at a high level very well. The book still leaves a few questions in my mind unanswered, but overall it has done a good job.
October 25, 2017
Comprehensive summary of data science
Great introduction for beginners. The author did a good job in using layman terms to explain how each algorithm works and provide the audience a general understanding of the big picture
Great introduction for beginners. The author did a good job in using layman terms to explain how each algorithm works and provide the audience a general understanding of the big picture
November 13, 2017
Best book for understanding the algorithms
This gave me a clear picture of what algorithms to be used and when. Best book and I would suggest it to all those who want to learn machine learning!!
This gave me a clear picture of what algorithms to be used and when. Best book and I would suggest it to all those who want to learn machine learning!!
August 22, 2018
Good Starting Book on Data Science & Algorithms
Good Book for Beginners - covers basics of Data Science and related Algorithms quite well. Recommended especially for Business Executives
Good Book for Beginners - covers basics of Data Science and related Algorithms quite well. Recommended especially for Business Executives
September 12, 2018
Explained with simple words and examples
This book is like a starter kit for all the machine learning enthusiasts. It touches almost all the sections right from classification to neural networks.
This book is like a starter kit for all the machine learning enthusiasts. It touches almost all the sections right from classification to neural networks.
November 3, 2019
It's a mostly OK book on Data Science, but it's unclear to me what you can learn from it.
On the upside, it's short. It covers a bunch of algorithms and gives you a sense of what Machine Learning is about.
On the downside, it's "a sense" at best. The idea is to not go into a lot of detail, but the delivery is mostly hand-waving. Pretty much nothing is explained in enough detail to be able to use it or understand it in any depth. Even the relatively simple stuff – like linear regression – is made far too simple to be useful. The examples are not well picked and in the absence of detail, there aren't enough metaphors to explain how things work.
Read it if you want to get a vague sense of what Machine Learning is about, but if you want to get into it, you would have to learn everything covered in this book properly, from a different source.
On the upside, it's short. It covers a bunch of algorithms and gives you a sense of what Machine Learning is about.
On the downside, it's "a sense" at best. The idea is to not go into a lot of detail, but the delivery is mostly hand-waving. Pretty much nothing is explained in enough detail to be able to use it or understand it in any depth. Even the relatively simple stuff – like linear regression – is made far too simple to be useful. The examples are not well picked and in the absence of detail, there aren't enough metaphors to explain how things work.
Read it if you want to get a vague sense of what Machine Learning is about, but if you want to get into it, you would have to learn everything covered in this book properly, from a different source.
Displaying 1 - 30 of 81 reviews