Active Machine Learning with Python : Refine and Elevate Data Quality over Quantity with Active Learning / Margaux Masson-Forsythe.

Format:

Book

Author/Creator:

Masson-Forsythe, Margaux, author.

Language:

English

Subjects (All):

Machine learning.

Python (Computer program language).

Data mining.

Physical Description:

1 online resource (176 pages)

Edition:

First edition.

Place of Publication:

Birmingham, England : Packt Publishing, [2024]

Biography/History:

Masson-Forsythe Margaux: Margaux Masson-Forsythe is a skilled machine learning engineer and advocate for advancements in surgical data science and climate AI. As the Director of Machine Learning at Surgical Data Science Collective, she builds computer vision models to detect surgical tools in videos and track procedural motions. Masson-Forsythe manages a multidisciplinary team and oversees model implementation, data pipelines, infrastructure, and product delivery. With a background in computer science and expertise in machine learning, computer vision, and geospatial analytics, she has worked on projects related to reforestation, deforestation monitoring, and crop yield prediction.

Summary:

Use active machine learning with Python to improve the accuracy of predictive models, streamline the data analysis process, and adapt to evolving data trends, fostering innovation and progress across diverse fields Key Features Learn how to implement a pipeline for optimal model creation from large datasets and at lower costs Gain profound insights within your data while achieving greater efficiency and speed Apply your knowledge to real-world use cases and solve complex ML problems Purchase of the print or Kindle book includes a free PDF eBook Book Description Building accurate machine learning models requires quality data--lots of it. However, for most teams, assembling massive datasets is time-consuming, expensive, or downright impossible. Led by Margaux Masson-Forsythe, a seasoned ML engineer and advocate for surgical data science and climate AI advancements, this hands-on guide to active machine learning demonstrates how to train robust models with just a fraction of the data using Python's powerful active learning tools. You'll master the fundamental techniques of active learning, such as membership query synthesis, stream-based sampling, and pool-based sampling and gain insights for designing and implementing active learning algorithms with query strategy and Human-in-the-Loop frameworks. Exploring various active machine learning techniques, you'll learn how to enhance the performance of computer vision models like image classification, object detection, and semantic segmentation and delve into a machine AL method for selecting the most informative frames for labeling large videos, addressing duplicated data. You'll also assess the effectiveness and efficiency of active machine learning systems through performance evaluation. By the end of the book, you'll be able to enhance your active learning projects by leveraging Python libraries, frameworks, and commonly used tools. What you will learn Master the fundamentals of active machine learning Understand query strategies for optimal model training with minimal data Tackle class imbalance, concept drift, and other data challenges Evaluate and analyze active learning model performance Integrate active learning libraries into workflows effectively Optimize workflows for human labelers Explore the finest active learning tools available today Who this book is for Ideal for data scientists and ML engineers aiming to maximize model performance while minimizing costly data labeling, this book is your guide to optimizing ML workflows and prioritizing quality over quantity. Whether you're a technical practitioner or team lead, you'll benefit from the proven methods presented in this book to slash data requirements and iterate faster. Basic Python proficiency and familiarity with machine learning concepts such as datasets and convolutional neural networks is all you need to get started.

Contents:

Cover

Title Page

Copyright and Credits

Contributors

Table of Contents

Preface

Part 1: Fundamentals of Active Machine Learning

Chapter 1: Introducing Active Machine Learning

Understanding active machine learning systems

Definition

Potential range of applications

Key components of active machine learning systems

Exploring query strategies scenarios

Membership query synthesis

Stream-based selective sampling

Pool-based sampling

Comparing active and passive learning

Summary

Chapter 2: Designing Query Strategy Frameworks

Technical requirements

Exploring uncertainty sampling methods

Understanding query-by-committee approaches

Maximum disagreement

Vote entropy

Average KL divergence

Labeling with EMC sampling

Sampling with EER

Understanding density-weighted sampling methods

Chapter 3: Managing the Human in the Loop

Designing interactive learning systems and workflows

Exploring human-in-the-loop labeling tools

Common labeling platforms

Handling model-label disagreements

Programmatically identifying mismatches

Manual review of conflicts

Effectively managing human-in-the-loop systems

Ensuring annotation quality and dataset balance

Assess annotator skills

Use multiple annotators

Balanced sampling

Part 2: Active Machine Learning in Practice

Chapter 4: Applying Active Learning to Computer Vision

Implementing active ML for an image classification project

Building a CNN for the CIFAR dataset

Applying uncertainty sampling to improve classification performance

Applying active ML to an object detection project

Preparing and training our model

Analyzing the evaluation metrics

Implementing an active ML strategy.

Using active ML for a segmentation project

Chapter 5: Leveraging Active Learning for Big Data

Implementing ML models for video analysis

Selecting the most informative frames with Lightly

Using Lightly to select the best frames to label for object detection

SSL with active ML

Part 3: Applying Active Machine Learning to Real-World Projects

Chapter 6: Evaluating and Enhancing Efficiency

Creating efficient active ML pipelines

Monitoring active ML pipelines

Determining when to stop active ML runs

Enhancing production model monitoring with active ML

Challenges in monitoring production models

Active ML to monitor models in production

Early detection for data drift and model decay

Chapter 7: Utilizing Tools and Packages for Active ML

Mastering Python packages for enhanced active ML

scikit-learn

modAL

Getting familiar with the active ML tools

Index

Other Books You May Enjoy.

Notes:

Description based on publisher supplied metadata and other sources.

Description based on print version record.

ISBN:

9781835462683

1835462685

OCLC:

1428526449