Machine Learning For Dummies

Your no-nonsense guide to making sense of machine learning Machine learning can be a mind-boggling concept for the masses, but those who are in the trenches of computer programming know just how invaluable it is. Without machine learning, fraud detection, web search results, real-time ads on web pages, credit scoring, automation, and email spam filtering wouldn't be possible, and this is only showcasing just a few of its capabilities. Written by two data science experts, Machine Learning For Dummies offers a much-needed entry point for anyone looking to use machine learning to accomplish practical tasks. Covering the entry-level topics needed to get you familiar with the basic concepts of machine learning, this guide quickly helps you make sense of the programming languages and tools you need to turn machine learning-based tasks into a reality. Whether you're maddened by the math behind machine learning, apprehensive about AI, perplexed by preprocessing data—or anything in between—this guide makes it easier to understand and implement machine learning seamlessly. Grasp how day-to-day activities are powered by machine learning Learn to 'speak' certain languages, such as Python and R, to teach machines to perform pattern-oriented tasks and data analysis Learn to code in R using R Studio Find out how to code in Python using Anaconda Dive into this complete beginner's guide so you are armed with all you need to know about machine learning! Title Page Table of Contents Introduction About This Book Foolish Assumptions Icons Used in This Book Beyond the Book Where to Go from Here Part 1: Introducing How Machines Learn Chapter 1: Getting the Real Story about AI Moving beyond the Hype Dreaming of Electric Sheep Overcoming AI Fantasies Considering the Relationship between AI and Machine Learning Considering AI and Machine Learning Specifications Defining the Divide between Art and Engineering Chapter 2: Learning in the Age of Big Data Defining Big Data Considering the Sources of Big Data Specifying the Role of Statistics in Machine Learning Understanding the Role of Algorithms Defining What Training Means Chapter 3: Having a Glance at the Future Creating Useful Technologies for the Future Discovering the New Work Opportunities with Machine Learning Avoiding the Potential Pitfalls of Future Technologies Part 2: Preparing Your Learning Tools Chapter 4: Installing an R Distribution Choosing an R Distribution with Machine Learning in Mind Installing R on Windows Installing R on Linux Installing R on Mac OS X Downloading the Datasets and Example Code Chapter 5: Coding in R Using RStudio Understanding the Basic Data Types Working with Vectors Organizing Data Using Lists Working with Matrices Interacting with Multiple Dimensions Using Arrays Creating a Data Frame Performing Basic Statistical Tasks Chapter 6: Installing a Python Distribution Choosing a Python Distribution with Machine Learning in Mind Installing Python on Linux Installing Python on Mac OS X Installing Python on Windows Downloading the Datasets and Example Code Chapter 7: Coding in Python Using Anaconda Working with Numbers and Logic Creating and Using Strings Interacting with Dates Creating and Using Functions Using Conditional and Loop Statements Storing Data Using Sets, Lists, and Tuples Defining Useful Iterators Indexing Data Using Dictionaries Storing Code in Modules Chapter 8: Exploring Other Machine Learning Tools Meeting the Precursors SAS, Stata, and SPSS Learning in Academia with Weka Accessing Complex Algorithms Easily Using LIBSVM Running As Fast As Light with Vowpal Wabbit Visualizing with Knime and RapidMiner Dealing with Massive Data by Using Spark Part 3: Getting Started with the Math Basics Chapter 9: Demystifying the Math Behind Machine Learning Working with Data Exploring the World of Probabilities Describing the Use of Statistics Chapter 10: Descending the Right Curve Interpreting Learning As Optimization Exploring Cost Functions Descending the Error Curve Updating by Mini-Batch and Online Chapter 11: Validating Machine Learning Checking Out-of-Sample Errors Getting to Know the Limits of Bias Keeping Model Complexity in Mind Keeping Solutions Balanced Training, Validating, and Testing Resorting to Cross-Validation Looking for Alternatives in Validation Optimizing Cross-Validation Choices Avoiding Sample Bias and Leakage Traps Chapter 12: Starting with Simple Learners Discovering the Incredible Perceptron Growing Greedy Classification Trees Taking a Probabilistic Turn Part 4: Learning from Smart and Big Data Chapter 13: Preprocessing Data Gathering and Cleaning Data Repairing Missing Data Transforming Distributions Creating Your Own Features Compressing Data Delimiting Anomalous Data Chapter 14: Leveraging Similarity Measuring Similarity between Vectors Using Distances to Locate Clusters Tuning the K-Means Algorithm Searching for Classification by K-Nearest Neighbors Leveraging the Correct K Parameter Chapter 15: Working with Linear Models the Easy Way Starting to Combine Variables Mixing Variables of Different Types Switching to Probabilities Guessing the Right Features Learning One Example at a Time Chapter 16: Hitting Complexity with Neural Networks Learning and Imitating from Nature Struggling with Overfitting Introducing Deep Learning Chapter 17: Going a Step beyond Using Support Vector Machines Revisiting the Separation Problem: A New Approach Explaining the Algorithm Applying Nonlinearity Illustrating Hyper-Parameters Classifying and Estimating with SVM Chapter 18: Resorting to Ensembles of Learners Leveraging Decision Trees Working with Almost Random Guesses Boosting Smart Predictors Averaging Different Predictors Part 5: Applying Learning to Real Problems Chapter 19: Classifying Images Working with a Set of Images Extracting Visual Features Recognizing Faces Using Eigenfaces Classifying Images Chapter 20: Scoring Opinions and Sentiments Introducing Natural Language Processing Understanding How Machines Read Using Scoring and Classification Chapter 21: Recommending Products and Movies Realizing the Revolution Downloading Rating Data Leveraging SVD Part 6: The Part of Tens Chapter 22: Ten Machine Learning Packages to Master Cloudera Oryx CUDA-Convnet ConvNetJS e1071 gbm Gensim glmnet randomForest SciPy XGBoost Chapter 23: Ten Ways to Improve Your Machine Learning Models Studying Learning Curves Using Cross-Validation Correctly Choosing the Right Error or Score Metric Searching for the Best Hyper-Parameters Testing Multiple Models Averaging Models Stacking Models Applying Feature Engineering Selecting Features and Examples Looking for More Data About the Author Advertisement Page Connect with Dummies End User License Agreement **Your no-nonsense guide to making sense of machine learning**Machine learning can be a mind-boggling concept for the masses, but those who are in the trenches of computer programming know just how invaluable it is. Without machine learning, fraud detection, web search results, real-time ads on web pages, credit scoring, automation, and email spam filtering wouldn't be possible, and this is only showcasing just a few of its capabilities. Written by two data science experts, __Machine Learning For Dummies__ offers a much-needed entry point for anyone looking to use machine learning to accomplish practical tasks. Covering the entry-level topics needed to get you familiar with the basic concepts of machine learning, this guide quickly helps you make sense of the programming languages and tools you need to turn machine learning-based tasks into a reality. Whether you're maddened by the math behind machine learning, apprehensive about AI, perplexed by preprocessing data—or anything in between—this guide makes it easier to understand and implement machine learning seamlessly. Grasp how day-to-day activities are powered by machine learning Learn to 'speak' certain languages, such as Python and R, to teach machines to perform pattern-oriented tasks and data analysis Learn to code in R using R Studio Find out how to code in Python using Anaconda Dive into this complete beginner's guide so you are armed with all you need to know about machine learning! Machine learning is an exciting new way to use computers to perform tasks that require the ability to learn from experience. In order to make machine learning a reality, programmers rely on special languages, such as Python and R, and new types of tools. Machine Learning For Dummies helps the reader understand what machine learning is, when it can help perform a new class of computer tasks, and how to implement machine learning using Python and R, along with the required tools. Unlike most machine learning books, Machine Learning For Dummies does not assume that the reader has years of experience using programming languages. This book provides the much-needed entry point for people who really could use machine learning to accomplish practical tasks, but dont necessarily have the skills required to use on more advanced books. This book will cover the entry level materials required to get readers up and running faster, how to perform practical tasks, how to perform useful work without getting overly involved in the underlying math principles, fun ways to play with new tools and learn as a result, and how to separate facts from myth to see how machine learning is useful in todays world. -- Publisher