Leanpub Header

Skip to main content

Filters

Category: "Machine Learning"

Machine Learning

  1. Machine Learning in Python for Dynamic Process Systems
    Machine Learning in Python for Dynamic Process Systems
    A practitioner’s guide for building process modeling, predictive, and monitoring solutions using dynamic data
    Ankur Kumar and Jesus Flores Cerrillo

    This book provides a comprehensive coverage of ML methods that have proven useful in process industry for dynamic process modeling. Step-by-step instructions, supported with industry-relevant case studies, show how to develop solutions for process modeling, process monitoring, etc., using classical and modern methods. Also available at Google Play 

  2. 解剖深度學習原理
    解剖深度學習原理
    從0實現深度學習庫
    hwdong

    市面上的深度學習書要么晦澀難懂,要么是平台使用說明書,只講理論缺少實現或者只有編程缺少原理講解,都很難讓人理解深度學習的基本原理,本書採用理論講解與代碼實現的方式深入淺出地剖析了深度學習的技術原理和實現細節,教會讀者如何從零編寫一個深度學習庫。內容包含了:梯度下降法、回歸學習、前饋神經網絡、卷積神經網絡、循環神經網絡、生成網絡。

  3. 深層学習原理の構造
    深層学習原理の構造
    深層学習ライブラリをゼロから作成する
    hwdong

    市場に出回っている深層学習の本は、あいまいで理解しにくいもの、またはプラットフォームの説明書であり、実装がなく理論だけが説明されているか、原理の説明がなくプログラミングだけが説明されているものであり、人々が深層学習の基本原理を理解することは困難です.この本では、理論的な説明とコードの実装を使用しています。この方法では、深層学習の技術原理と実装の詳細を簡単な方法で分析し、深層学習ライブラリをゼロから作成する方法を読者に教えています。コンテンツには、勾配降下法、回帰学習、フィードフォワード ニューラル ネットワーク、畳み込みニューラル ネットワーク、再帰型ニューラル ネットワーク、生成ネットワークが含まれます。

  4. AI-Powered Data Products
    AI-Powered Data Products
    Transforming Data into Profit: A C-Suite Handbook
    Jarkko Moilanen, PhD and Venkata Pradeep Tatiraju

    From machine learning to natural language processing, this book will guide you through the cutting-edge world of AI-powered data products. You'll learn how to harness the power of AI to create products that are smarter, faster, and more efficient than anything your competitors can dream of.

  5. Anatomy of Deep Learning Principles
    Anatomy of Deep Learning Principles
    Writing a Deep Learning Library from Scratch
    hwdong

    Talking about theory without implementation or only programming without principle explanations is difficult for people to understand the principles of deep learning. This book uses theoretical explanations and code implementations to explain the principles of deep learning and how to write a deep learning library from scratch.

  6. Statistics with Rust
    Statistics with Rust
    50+ Statistical Techniques Put into Action
    GitforGits | Asian Publishing House

    "Statistics with Rust" is your comprehensive resource to unlock Rust's true potential in modern statistical methods.

  7. Learning Pandas 2.0
    Learning Pandas 2.0
    A Comprehensive Guide to Data Manipulation and Analysis for Data Scientists and Machine Learning Professionals
    GitforGits | Asian Publishing House

    Using Pandas 2.0, setting you on the path to becoming a data analysis powerhouse

  8. Get SH*T Done with Prompt Engineering and LangChain
    Get SH*T Done with Prompt Engineering and LangChain
    Build AI Applications with ChatGPT in Python
    Venelin Valkov

    Will AI replace you, or will you use AI to 10x yourself? Discover the secrets of Prompt Engineering and LangChain to build chatbots, summarization tools, and more. Get ready to revolutionize the way you approach AI development with this comprehensive guide.

  9. AI Domination: Chat GPT-3.5 Guide

    Discover: the ultimate Chat GPT-3.5 guide that will leave you wondering if your AI assistant has taken over! With witty humor and helpful tips.AI Domination: GPT-3.5 Guide is a must-read for anyone wanting to unlock the full potential of Chat GPT. Get your copy today and join the AI revolution!

  10. The McGinty Equation
    The McGinty Equation
    Unifying Quantum Field Theory and Fractal Theory to Understand Subatomic Particle Behavior
    Chris McGinty

    Beyond practical applications, the McGinty Equation underscores the beauty and elegance of physics, demonstrating how theoretical concepts can be used to solve complex problems and uncover new truths about the universe. Its potential applications extend beyond quantum mechanics and into other fields, such as biology, finance, and computer science.

  11. OpenAI GPT For Python Developers
    OpenAI GPT For Python Developers
    The art and science of building AI-powered apps with GPT-4, Whisper, Weaviate, and beyond
    Aymen El Amri

    Explore the fascinating world of Artificial Intelligence and solve real-world problems! In this practical guide, you will build intelligent real-world applications using GPT-4, Embeddings, Whisper, Weaviate, and more tools from the OpenAI ecosystem. You don't need to be a data scientist or machine learning engineer to follow this guide!

  12. Supervised Machine Learning မိတ်ဆက်
    Supervised Machine Learning မိတ်ဆက်
    Regression and Classification
    myothida (ဒေါက်တာမျိုးသီတာ)

    Machine Learning ၏ အဓိပ္ပာယ်ကို လူအများစု အလွယ်တကူ နားလည်နိုင်ရန် အဓိပ္ပာယ် ဖွင့်ဆိုရမည်ဆိုပါက ကွန်ပြူတာ (သို့မဟုတ်) စက် တစ်ခုခုကို လူ့ကိုယ်စား (သို့မဟုတ်) လူကဲ့သို့ ပြုမူဆောင်ရွက်နိုင်စေရန် သင်ကြားပေးခြင်းဟု ယေဘုယျ ဖွင့်ဆို နိုင်ပါသည်။ဥပမာ ပေးရမည် ဆိုပါက ၂၀၂၂ ခုနှစ် နို၀င်ဘာလတွင် OpenAI မှ စတင် ထုတ်လိုက်သည့် ChatGPT ဖြစ်သည်။

  13. Introduction to Supervised Machine Learning
    Introduction to Supervised Machine Learning
    Regression and Classification
    myothida

    A newly released AI invention, ChatGPT is able to answer questions and even write code for developers. Does this information make you feel that understanding Machine Learning might be challenging for you? This book provides a comprehensive and easy-to-follow introduction to the fundamental concepts of machine learning methods.

  14. Feature Engineering & Selection for Explainable Models
    Feature Engineering & Selection for Explainable Models
    A Second Course for Data Scientists (Revised Edition)
    Md Azimul Haque
    No Description Available
  15. Data Cleaning: The Ultimate Practical Guide
    Data Cleaning: The Ultimate Practical Guide
    From Dirty Data to Clean Data
    Lee Baker

    Data Cleaning: The Ultimate Practical Guide is a guide to understanding what dirty data is, and how it gets into your dataset.This book will help you prevent most types of dirty data getting into your dataset, and clean out quickly and efficiently the remaining errors, so you can have clean, fit-for-purpose and analysis-ready data.