

Buy anything from 5,000+ international stores. One checkout price. No surprise fees. Join 2M+ shoppers on Desertcart.
Desertcart purchases this item on your behalf and handles shipping, customs, and support to Netherlands.
This accessible guide walks you through the math necessary to thrive in the AI field such as focusing on real-world applications rather than dense academic theory. Engineers, data scientists, and students alike will examine mathematical topics critical for AI--including regression, neural networks, optimization, backpropagation, convolution, Markov chains, and more--through popular applications such as computer vision, natural language processing, and automated systems. Review: AI must - An ideal purchase for anyone going further in AI. Review: Horrible book. - One of the worst books (or maybe even the worst) in this topic that I have ever read. The author is extremely confused about what this book is supposed to be. The book is not technical, but it's also not narration based, it is not appropriate for advanced practitioners of ML but it also is not really suitable for beginners either as there are virtually no basics explained (at least not sufficiently). I honestly just got annoyed reading it, and did not get much out of it. There other titles in this topic, which are written much better and are a significantly better investment of your time and money. I do not recommend.



















| Best Sellers Rank | 199,500 in Books ( See Top 100 in Books ) 202 in Higher Mathematical Education 2,093 in Computer Science (Books) 8,607 in Scientific, Technical & Medical |
| Customer Reviews | 4.3 out of 5 stars 86 Reviews |
P**3
AI must
An ideal purchase for anyone going further in AI.
A**R
Horrible book.
One of the worst books (or maybe even the worst) in this topic that I have ever read. The author is extremely confused about what this book is supposed to be. The book is not technical, but it's also not narration based, it is not appropriate for advanced practitioners of ML but it also is not really suitable for beginners either as there are virtually no basics explained (at least not sufficiently). I honestly just got annoyed reading it, and did not get much out of it. There other titles in this topic, which are written much better and are a significantly better investment of your time and money. I do not recommend.
B**B
In-depth AI Background
Hala Nelson gives a well-structured introduction to the concepts and the mathematical tools that form the basis of AI and data science. Some chapters are tough reading, but the insight and the profound understanding gained from working through the math are well worth the effort. Some experience with current AI or data analytics tools is helpful for understanding the concepts, but generally the text is self-explanatory. After reading the book, I feel much more secure in the vast and rapidly expanding field of AI and data science.
E**A
Bom
Bom
Y**A
AI関連技術の数学
本書は、機械学習に関してトピックごとに関連する数学が挿入してあります。数学の理論や証明、プラミングコードは記述してありません。 読者として、数学を専門にするものだけでなく、データサイエンティスト、AI、機械学習エンジニア、技術の倫理的な問題に関わる思索者、AIやデータ分析を業務に組み入れたいと考える管理職、他の領域を専門とするAIに興味のある人々を対象にしてあります。 本書で取り上げているAI・機械学習の主なトピックは以下のようなものです。 ・一般的なトレーニング関数、損失関数、最適化 ・画像認識とCNN ・SVD(主成分分析と次元の縮約)と画像処理、自然言語処理、 ・自然言語処理に関する量子化と時系列分析 ・確率的な生成モデル ・グラフモデル ・オペレーション・リサーチ ・因果関係におけるPearlのdo-calculas ・AIと偏微分方程式 情報処理のシステムとして、ルールをプログラムし、それらの予めプログラムされたルールに基づいて、決定し、結論を得る代わりに、機械学習はデータからルールを推論します。そのため機械学習では、最初にデータが必要になります。 一般的なアルゴリズムの構成法は、問題を識別してモデルを作り、データに関数を適合させます。 ニューラルネットの最適化には確率勾配下降法が用いられますが、これは類書でも多く解説されています。 本書で取り上げているユニークなテーマとして、オペレーション・リサーチや偏微分方程式に独立した章が割り当てられています。 ニューラルネットでは任意の関数を再現できることがわかっています。偏微分方程式の章では、ニューラルネットワークは、任意の関数を無限の次元の空間にマッピングして近似することができ、どのような非線形の連続した関数でも近似することができることなどが記述されています。 各トピックに沿って、概念の説明に数学が用いられています。 各章のトピックは独立しており、初めの章から順番に進める必要はなく、興味のあるテーマから読める構成になっています。 教養として技術的背景にある数学を知るには良いでしょう。より深く技術を把握しておきたければ、Kindle版は本文中に関連資料へのリンクが貼ってあるので簡単に参照することができます。
S**Z
Genial
Muy buen libro, todos los fundamentos bien explicados, perfecto para ahondar en la IA
E**R
Great Book
This is a great book. It provides a great high-level overview of diverse AI-related topics. I am currently a graduate student working on my PhD research. Although it is written in a simple language, it clarified a lot of the concepts that I had encountered earlier but had doubts. It clarifies the relation between one type of model and another. For example, SVDs relationship with PCA and with Eigenvalue decomposition. And that too without reading a lot of other technical references and books. It has some Maths but I wish it had a little more Math or references. Although a lot of work is done on the NLP chapter, it is a big chapter and it still might have been better to add details to various vector representations. Overall I like this book to suggest it to my friends.
Trustpilot
2 weeks ago
1 week ago