著書

I wrote this book entitled "Designing Intelligent Electronic Toys Using Flash Microcontrollers" in 2005. Unfortunately, the book has never been published. Therefore, this book had been a phantom book. This renamed book is still useful in IoT era. This book highlights three projects: banner badge, 8-queen neural network (8-bit microcontroller solves 8-queen problems based on neural network), and artificial retina camera (this is the world-first camera for mobile phones). This book is intended for practitioners or novice/professional readers who are interested in designing, developing, and building intelligent electronic gadgets or ubiquitous toys using flash microcontrollers. Two microcontrollers are mainly introduced and used through this book: ATMEL and CYGNAL microcontrollers. A variety of applications using networking devices, sensors, and actuators with microcontollers are detailed by using many circuit diagrams, software source programs, and figures for practitioners. This introductory book can be used as the text or one of the references in high schools or universities for building embedded ubiquitous or wearable computers.

This book illustrates how to build a GPU parallel computer. If you don't want to waste your time for building, you can buy a built-in-GPU desktop/laptop machine. All you need to do is to install GPU-enabled software for parallel computing. The GPU parallel computer is suitable for machine learning, deep (neural network) learning. Two operating system examples including Ubuntu16.04 and Windows 10 system will be described. This book shows how to install CUDA and cudnnlib in two operating systems. Three frameworks including pytorch, keras, and chainer for machine learning on CUDA and cudnnlib will be introduced. Matching problems between operating system (Ubuntu, Windows 10), library (CUDA, cudnnlib), and machine learning framework (pytorch, keras, chainer) are discussed.

安価なハードウェアでIoT設計!! 本書は,安価なハードウェア(Arduino,NanoPi NEOや,ドローンの制御センサー他)を駆使したIoT設計で,2Dレーザー彫刻,LPWAN通信,気象観測,機械学習,自動情報収集など,様々なIoTデバイス設計・製作に挑戦する! 電子回路の基礎を体験的に学べるようになっているので,中・上級者はもちろん,初心者でも体験的に実践することができる. Arduino,NanoPi NEOなどでIoT設計に挑戦する読者には、必携の指南書である.

本書は、ポスト深層学習の最右翼として注目される「アンサンブル機械学習」を、具体的にプログラムを動かしながら概観できる“超実践"の書です。 アンサンブル機械学習とは簡単に言えば、従来のいくつかの機械学習の“良いとこ取り"をした計算手法です。本書では、その主な要素である「ランダムフォーレスト」、「ブースティング」、「バギング」などについて簡潔に紹介しました。 「とにかく使ってみたい! 」という読者にはうってつけの、まさに“超実践の必読書"と言えます。

This book illustrates how to implement ensemble machine learning programs in Python using scikit-learn which is one of the best open source machine learning libraries for businessman or businesswoman. This book is suitable to the interested layman who would like to analyze big data without serious programming in Python. Three examples are illustrated how to use ensemble machine learning for big data analysis. In the first example, rules between poker hands (five cards) and their rankings can be trained using ensemble machine learning. In the second example, the conventional multiple regression method is compared with the ensemble machine learning by using ice cream sales with data of the daily high temperature and the number of passers-by. In the last example, Artificial wine sommelier is built by red wine quality data. The illustrated ensemble machine learning includes AdaBoost, Bagging, ExtraTrees, GradientBoosting, and RandomForest. The grid-search example is introduced for parameter tuning.

本書は、最先端の人工知能の集合体であるオープンソース機械学習（scikit-learn)を活用して、ビジネスマンがビッグデータ分析するための入門書です。従来の統計手法・分析では出来なかった"正確な予測", "データの自動特徴分析", "データモデルの自動構築"を実現するために、アンサンブル機械学習ライブラリを活用します。本書では、プログラミングの素人でも簡単にビッグデータ分析・活用・実践できるように、Python言語による３つのプログラム例を紹介します。１つは、データを与えて10種類のポーカーの役を機械学習する例、2つ目はワインの品質を格付けできる人工ソムリエの例です。また、重回帰分析とアンサンブル機械学習の予測性能を比較します。アンサンブル機械学習では、AdaBoost、Bagging、ExtraTrees、GradientBoosting、 RandomForestなどの手法を使った事例のソースコードを公開します。