Bücher von Sinan Ozdemir

This book bridges the gap between mathematics and computer science to show you how to gain actionable insights from your data. You'll explore the entire data science pipeline while learning effective data mining techniques and the fundamentals of computational mathematics and statistics to create powerful data visualizations.

Transform your data into insights with must-know techniques and mathematical concepts to unravel the secrets hidden within your dataKey Features:- Learn practical data science combined with data theory to gain maximum insights from data- Discover methods for deploying actionable machine learning pipelines while mitigating biases in data and models- Explore actionable case studies to put your new skills to use immediately- Purchase of the print or Kindle book includes a free PDF eBookBook Description:Principles of Data Science bridges mathematics, programming, and business analysis, empowering you to confidently pose and address complex data questions and construct effective machine learning pipelines. This book will equip you with the tools to transform abstract concepts and raw statistics into actionable insights.Starting with cleaning and preparation, you'll explore effective data mining strategies and techniques before moving on to building a holistic picture of how every piece of the data science puzzle fits together. Throughout the book, you'll discover statistical models with which you can control and navigate even the densest or the sparsest of datasets and learn how to create powerful visualizations that communicate the stories hidden in your data.With a focus on application, this edition covers advanced transfer learning and pre-trained models for NLP and vision tasks. You'll get to grips with advanced techniques for mitigating algorithmic bias in data as well as models and addressing model and data drift. Finally, you'll explore medium-level data governance, including data provenance, privacy, and deletion request handling.By the end of this data science book, you'll have learned the fundamentals of computational mathematics and statistics, all while navigating the intricacies of modern ML and large pre-trained models like GPT and BERT.What You Will Learn:- Master the fundamentals steps of data science through practical examples- Bridge the gap between math and programming using advanced statistics and ML- Harness probability, calculus, and models for effective data control- Explore transformative modern ML with large language models- Evaluate ML success with impactful metrics and MLOps- Create compelling visuals that convey actionable insights- Quantify and mitigate biases in data and ML modelsWho this book is for:If you are an aspiring novice data scientist eager to expand your knowledge, this book is for you. Whether you have basic math skills and want to apply them in the field of data science, or you excel in programming but lack the necessary mathematical foundations, you'll find this book useful. Familiarity with Python programming will further enhance your learning experience.Table of Contents- Data Science Terminology- Types of Data- The Five Steps of Data Science- Basic Mathematics- Impossible or Improbable - A Gentle Introduction to Probability- Advanced Probability- What are the Chances? An Introduction to Statistics- Advanced Statistics- Communicating Data- How to Tell if Your Toaster is Learning - Machine Learning Essentials- Predictions Don't Grow on Trees, or Do They?- Introduction to Transfer Learning and Pre-trained Models- Mitigating Algorithmic Bias and Tackling Model and Data Drift- AI Governance- Navigating Real-World Data Science Case Studies in Action

Der Schnellstart in die praktische Arbeit mit LLMs Das Buch bietet einen Überblick über zentrale Konzepte und Techniken von LLMs wie z.B. ChatGPT und zeigt das Potenzial von Open-Source- und Closed-Source-Modellen Es erläutert, wie Large Language Models funktionieren und wie sie für Aufgaben des Natural Language Processing (NLP) genutzt werden Auch für interessierte Nicht-Data-Scientists mit Python-Kenntnissen verständlich Themen z.B.: die ChatGPT-API, Prompt-Engineering, Chatbot-Personas, Cloud-Bereitstellung; deckt auch GPT-4 ab Large Language Models (LLMs) wie ChatGPT sind enorm leistungsfähig, aber auch sehr komplex. Praktikerinnen und Praktiker stehen daher vor vielfältigen Herausforderungen, wenn sie LLMs in ihre eigenen Anwendungen integrieren wollen. In dieser Einführung räumt Data Scientist und KI-Unternehmer Sinan Ozdemir diese Hürden aus dem Weg und bietet einen Leitfaden für den Einsatz von LLMs zur Lösung praktischer Probleme des Natural Language Processings. Sinan Ozdemir hat alles zusammengestellt, was Sie für den Einstieg benötigen: Schritt-für-Schritt-Anleitungen, Best Practices, Fallstudien aus der Praxis, Übungen und vieles mehr. Er stellt die Funktionsweise von LLMs vor und unterstützt Sie so dabei, das für Ihre Anwendung passende Modell und geeignete Datenformate und Parameter auszuwählen. Dabei zeigt er das Potenzial sowohl von Closed-Source- als auch von Open-Source-LLMs wie GPT-3, GPT-4 und ChatGPT, BERT und T5, GPT-J und GPT-Neo, Cohere sowie BART. Lernen Sie die Schlüsselkonzepte kennen: Transfer Learning, Feintuning, Attention, Embeddings, Tokenisierung und mehr Nutzen Sie APIs und Python, um LLMs an Ihre Anforderungen anzupassen Beherrschen Sie Prompt-Engineering-Techniken wie Ausgabe-Strukturierung, Gedankenketten und Few-Shot-Prompting Passen Sie LLM-Embeddings an, um eine Empfehlungsengine mit eigenen Benutzerdaten neu zu erstellen Konstruieren Sie multimodale Transformer-Architekturen mithilfe von Open-Source-LLMs Optimieren Sie LLMs mit Reinforcement Learning from Human and AI Feedback (RLHF/RLAIF) Deployen Sie Prompts und benutzerdefinierte, feingetunte LLMs in die Cloud

The book will allow readers to implement smart solutions to their existing cybersecurity products and effectively build intelligent solutions which cater to the needs of the future. By the end of this book, you will be able to build, apply, and evaluate machine learning algorithms to identify various cybersecurity potential threats.

Feature engineering is the most important step in creating powerful machine learning systems. This book will take you through the entire feature-engineering journey to make your machine learning much more systematic and effective.