Machine Learning Yearning by Andrew Ng
Hello, we invite you to join our data science team at AllMyth Coverage, an insurance company that covers mythical creatures. Dragons, unicorns, and plenty of odd edge cases included.
Instead of listing algorithms in isolation, we put models to work in a commercial setting. Together, we build, train, and analyze supervised learning models for classification and regression, always connecting the mathematics to the code and to real business decisions.
We cover risk classification using decision trees, random forests, and gradient boosted trees. For regression, we explore linear, weighted, and Bayesian regression. We also tackle churn prediction using perceptrons, logistic regression, and neural networks.
Along the way, we deal with overfitting, hyperparameter tuning, regularization techniques such as L1, L2, and dropout, and practical feature engineering. Every model is derived step by step, explained with hand worked examples, and then implemented in code.
This book assumes basic knowledge of linear algebra, calculus, probability and statistics, and Python. It is written for readers who want to understand how supervised learning models actually work, not just how to use them.
Original: $1.22
-65%$1.22
$0.43Machine Learning Yearning by Andrew Ng
Hello, we invite you to join our data science team at AllMyth Coverage, an insurance company that covers mythical creatures. Dragons, unicorns, and plenty of odd edge cases included.
Instead of listing algorithms in isolation, we put models to work in a commercial setting. Together, we build, train, and analyze supervised learning models for classification and regression, always connecting the mathematics to the code and to real business decisions.
We cover risk classification using decision trees, random forests, and gradient boosted trees. For regression, we explore linear, weighted, and Bayesian regression. We also tackle churn prediction using perceptrons, logistic regression, and neural networks.
Along the way, we deal with overfitting, hyperparameter tuning, regularization techniques such as L1, L2, and dropout, and practical feature engineering. Every model is derived step by step, explained with hand worked examples, and then implemented in code.
This book assumes basic knowledge of linear algebra, calculus, probability and statistics, and Python. It is written for readers who want to understand how supervised learning models actually work, not just how to use them.
Product Information
Product Information
Shipping & Returns
Shipping & Returns
Description
Hello, we invite you to join our data science team at AllMyth Coverage, an insurance company that covers mythical creatures. Dragons, unicorns, and plenty of odd edge cases included.
Instead of listing algorithms in isolation, we put models to work in a commercial setting. Together, we build, train, and analyze supervised learning models for classification and regression, always connecting the mathematics to the code and to real business decisions.
We cover risk classification using decision trees, random forests, and gradient boosted trees. For regression, we explore linear, weighted, and Bayesian regression. We also tackle churn prediction using perceptrons, logistic regression, and neural networks.
Along the way, we deal with overfitting, hyperparameter tuning, regularization techniques such as L1, L2, and dropout, and practical feature engineering. Every model is derived step by step, explained with hand worked examples, and then implemented in code.
This book assumes basic knowledge of linear algebra, calculus, probability and statistics, and Python. It is written for readers who want to understand how supervised learning models actually work, not just how to use them.
