Practical Full Stack Machine Learning
Download Practical Full Stack Machine Learning PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Practical Full Stack Machine Learning book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Practical Full Stack Machine Learning
Master the ML process, from pipeline development to model deployment in production. KEY FEATURES ● Prime focus on feature-engineering, model-exploration & optimization, dataops, ML pipeline, and scaling ML API. ● A step-by-step approach to cover every data science task with utmost efficiency and highest performance. ● Access to advanced data engineering and ML tools like AirFlow, MLflow, and ensemble techniques. DESCRIPTION 'Practical Full-Stack Machine Learning' introduces data professionals to a set of powerful, open-source tools and concepts required to build a complete data science project. This book is written in Python, and the ML solutions are language-neutral and can be applied to various software languages and concepts. The book covers data pre-processing, feature management, selecting the best algorithm, model performance optimization, exposing ML models as API endpoints, and scaling ML API. It helps you learn how to use cookiecutter to create reusable project structures and templates. It explains DVC so that you can implement it and reap the same benefits in ML projects.It also covers DASK and how to use it to create scalable solutions for pre-processing data tasks. KerasTuner, an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search will be covered in this book. It explains ensemble techniques such as bagging, stacking, and boosting methods and the ML-ensemble framework to easily and effectively implement ensemble learning. The book also covers how to use Airflow to automate your ETL tasks for data preparation. It explores MLflow, which allows you to train, reuse, and deploy models created with any library. It teaches how to use fastAPI to expose and scale ML models as API endpoints. WHAT YOU WILL LEARN ● Learn how to create reusable machine learning pipelines that are ready for production. ● Implement scalable solutions for pre-processing data tasks using DASK. ● Experiment with ensembling techniques like Bagging, Stacking, and Boosting methods. ● Learn how to use Airflow to automate your ETL tasks for data preparation. ● Learn MLflow for training, reprocessing, and deployment of models created with any library. ● Workaround cookiecutter, KerasTuner, DVC, fastAPI, and a lot more. WHO THIS BOOK IS FOR This book is geared toward data scientists who want to become more proficient in the entire process of developing ML applications from start to finish. Knowing the fundamentals of machine learning and Keras programming would be an essential requirement. TABLE OF CONTENTS 1. Organizing Your Data Science Project 2. Preparing Your Data Structure 3. Building Your ML Architecture 4. Bye-Bye Scheduler, Welcome Airflow 5. Organizing Your Data Science Project Structure 6. Feature Store for ML 7. Serving ML as API
Practical Machine Learning: From Pictures to the Cloud 2025
Author: AUTHOR:1-Praneet Amul Akash Cherukuri AUTHOR:2-Dr. Santosh Kumar Henge
language: en
Publisher: RAVEENA PRAKASHAN OPC PVT LTD
Release Date:
PREFACE The past decade has moved machine learning from academic curiosity to an invisible utility pulsing through every photograph we snap and every swipe we make. A face unlocks a phone, a drone inspects a bridge, a doctor consults an algorithm before a diagnosis—all powered by models that see, learn, and act in real time. Yet for students and engineers stepping into the field, the journey from inquisitive “Hello-world” notebook to a production-grade model running on an edge device or a cloud endpoint can feel disjointed and opaque. Practical Machine Learning: From Pictures to the Cloud was born of that gap. In our classrooms and industry collaborations at S R University, we watched learners master isolated concepts—convolutional layers, hyper-parameter tuning, REST APIs—without a blueprint that tied them together. This book offers that blueprint. We start with raw pixels, guide you through feature engineering and modern deep-learning architectures, and then scale the conversation outward: how to train responsibly, deploy at cloud scale, monitor for drift, and govern for fairness and privacy. What makes the text “practical” is its bias toward end-to-end reproducibility. Every chapter couple’s theory with hands-on labs drawn from real engagements in health care, smart cities, retail, and autonomous systems. Code examples ship as containerised notebooks; pipeline diagrams map directly to the managed services of AWS, Google Cloud, Azure, and open-source stacks like Kubeflow and Feast. Whether your workstation is a laptop or a GPU cluster, you can follow the same lifecycle we use in production. Equally vital is the ethical lens threaded throughout. As image models grow more capable, they also magnify risks—bias, surveillance, ecological cost. You will find checklists, case studies, and policy references alongside optimisation tricks, because robustness and responsibility are no longer optional extras; they are success criteria. The book is organised in three movements: 1. Seeing – fundamentals of image data, classical vision, and modern convolutional/transformer networks. 2. Learning – advanced training techniques, transfer learning, hyper-parameter tuning, and explainability. 3. Serving – scalable pipelines, cloud deployment, edge inference, monitoring, cost governance, and compliance. Our intended audience spans senior undergraduates, graduate students, and practitioners who know basic Python and linear algebra but want to take the leap into full-stack machine-learning engineering. We owe gratitude to our students, whose incisive questions shaped the narrative, and to industry partners who opened their architectures for case studies. Any errors that remain are ours alone. We hope this book becomes your desk companion as you turn pixels into insights and models into value—responsibly, reproducibly, and at scale. Authors
Deep Learning and Practice with MindSpore
This book systematically introduces readers to the theory of deep learning and explores its practical applications based on the MindSpore AI computing framework. Divided into 14 chapters, the book covers deep learning, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), unsupervised learning, deep reinforcement learning, automated machine learning, device-cloud collaboration, deep learning visualization, and data preparation for deep learning. To help clarify the complex topics discussed, this book includes numerous examples and links to online resources.