Book Image

AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

By : Somanath Nanda, Weslley Moura
Book Image

AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

By: Somanath Nanda, Weslley Moura

Overview of this book

The AWS Certified Machine Learning Specialty exam tests your competency to perform machine learning (ML) on AWS infrastructure. This book covers the entire exam syllabus using practical examples to help you with your real-world machine learning projects on AWS. Starting with an introduction to machine learning on AWS, you'll learn the fundamentals of machine learning and explore important AWS services for artificial intelligence (AI). You'll then see how to prepare data for machine learning and discover a wide variety of techniques for data manipulation and transformation for different types of variables. The book also shows you how to handle missing data and outliers and takes you through various machine learning tasks such as classification, regression, clustering, forecasting, anomaly detection, text mining, and image processing, along with the specific ML algorithms you need to know to pass the exam. Finally, you'll explore model evaluation, optimization, and deployment and get to grips with deploying models in a production environment and monitoring them. By the end of this book, you'll have gained knowledge of the key challenges in machine learning and the solutions that AWS has released for each of them, along with the tools, methods, and techniques commonly used in each domain of AWS ML.
Table of Contents (14 chapters)
Section 1: Introduction to Machine Learning
Section 2: Data Engineering and Exploratory Data Analysis
Section 3: Data Modeling

Modeling expectations

So far, we have talked about model building, validation, and management. Let's complete the foundations of ML by talking about a couple of other expectations while modeling.

The first one is parsimony. Parsimony describes models that offer the simplest explanation and fits the best results when compared with other models. Here's an example: while creating a linear regression model, you realize that adding 10 more features will improve your model performance by 0.001%. In this scenario, you should consider whether this performance improvement is worth the cost of parsimony (since your model will become more complex). Sometimes it is worth it, but most of the time it is not. You need to be skeptical and think according to your business case.

Parsimony directly supports interpretability. The simpler your model is, the easier it is to explain it. However, there is a battle between interpretability and predictivity: if you focus on predictive power, you are likely to lose some interpretability. Again, be a proper data scientist and select what is better for your use case.