Gerald Friedland – författare

Learn programming using the Commodore 16/Plus 4 system. Following this book, you and your children will not only learn BASIC programming, but also have fun emulating a retro Commodore system. There are many ways to bring the fun of learning to program in the 1980s back to life. For example, downloading the VICE emulator to a Raspberry Pi allows for the classic “turn on and program” experience and also provides some retro computing project fun. Many parents learned programming in this same way and can have fun helping their children follow the same path.

You can also use this book as an opportunity to dust off your computing skills or learn programming concepts for the first time on a system that’s easy, approachable, and fun with a nostalgic twist.

Commodore computers were the most sold computing devices before the iPhone. Nowadays, the Commodore system can be run using freely available emulation on modern computers. This book uses VICE,which is available for PC, Mac, Linux, as an online app, and on the Raspberry Pi. Beginning Programming Using Retro Computing offers simple programming concepts to give children and adults alike a sense of wonder in seeing that words they write have the power to do things, like play sounds, draw graphics, or finish math homework.

This groundbreaking book transcends traditional machine learning approaches by introducing information measurement methodologies that revolutionize the field.

Stemming from a UC Berkeley seminar on experimental design for machine learning tasks, these techniques aim to overcome the ''black box'' approach of machine learning by reducing conjectures such as magic numbers (hyper-parameters) or model-type bias. Information-based machine learning enables data quality measurements, a priori task complexity estimations, and reproducible design of data science experiments. The benefits include significant size reduction, increased explainability, and enhanced resilience of models, all contributing to advancing the discipline''s robustness and credibility.

While bridging the gap between machine learning and disciplines such as physics, information theory, and computer engineering, this textbook maintains an accessible and comprehensive style, making complex topics digestible fora broad readership. Information-Driven Machine Learning explores the synergistic harmony among these disciplines to enhance our understanding of data science modeling. Instead of solely focusing on the "how," this text provides answers to the "why" questions that permeate the field, shedding light on the underlying principles of machine learning processes and their practical implications. By advocating for systematic methodologies grounded in fundamental principles, this book challenges industry practices that have often evolved from ideologic or profit-driven motivations. It addresses a range of topics, including deep learning, data drift, and MLOps, using fundamental principles such as entropy, capacity, and high dimensionality.

Ideal for both academia and industry professionals, this textbook serves as a valuable tool for those seeking to deepen their understanding of data science as an engineering discipline. Its thought-provoking content stimulates intellectual curiosity and caters to readers who desire more than just code or ready-made formulas. The text invites readers to explore beyond conventional viewpoints, offering an alternative perspective that promotes a big-picture view for integrating theory with practice. Suitable for upper undergraduate or graduate-level courses, this book can also benefit practicing engineers and scientists in various disciplines by enhancing their understanding of modeling and improving data measurement effectively.

Dieses innovative Lehrbuch revolutioniert das maschinelle Lernen durch neue Informationsmessungsmethoden. Es basiert auf einem Seminar der UC Berkeley und zielt darauf ab, die Black-Box-Natur des maschinellen Lernens zu überwinden, indem es Datenqualitätsmessungen und A-priori-Schätzungen der Aufgabenkomplexität ermöglicht. Dies führt zu kleineren, erklärbareren und robusteren Modellen.

Das Lehrbuch verbindet maschinelles Lernen mit Physik, Informationstheorie und Computertechnik und ist für ein breites Publikum verständlich. Es hinterfragt bestehende Branchenpraktiken und behandelt Themen wie Deep Learning und Datendrift. Geeignet für Akademiker und Industrieprofis, fördert es ein tiefgreifendes Verständnis von Data Science und lädt Leser ein, über konventionelle Ansätze hinauszudenken. Anstatt sich ausschließlich auf das „Wie“ zu konzentrieren, bietet dieser Text Antworten auf die „Warum“-Fragen, die das Fachgebiet durchdringen, und beleuchtet die zugrunde liegenden Prinzipien maschineller Lernprozesse und ihre praktischen Auswirkungen. Indem dieses Buch systematische Methoden bevorzugt, die auf physikalischen Grundprinzipien basieren, stellt es Branchenpraktiken in Frage, die oft aus ideologischen oder gewinnorientierten Motivationen entstanden sind. Es behandelt eine Reihe von Themen, darunter Deep Learning, Datendrift und MLOps, und nutzt ausgiebig grundlegende Konzepte wie Entropie, Kapazität und hohe Dimensionalität.