menu
{ "item_title" : "Modern Deep Learning Foundation", "item_author" : [" Barak Or "], "item_description" : "This is not just another deep learning book. Modern Deep Learning Foundations is a complete, hands-on guide for building, training, and deploying neural networks - written specifically for engineers who care about real-world systems, not just theoretical results.Dr. Barak Or is an AI researcher, entrepreneur, and educator, with a PhD in ML for navigation systems, and a professional background that spans startups, deeptech technologies, and teaching at the Google-Reichman Tech School. He holds dual degrees in aeronautical engineering and economics & management from the Technion and has trained thousands of engineers across domains.What's Inside:Clear explanations of modern architectures: CNNs, RNNs, LSTMs, Transformers, Autoencoders, and moreIn-depth coverage of training essentials: loss functions, backpropagation, optimization (AdamW, Lion, Adafactor), mixed precision, and regularizationPractical tools for industrial use: saving and versioning models, serving with FastAPI, and deploying to the cloud with full PyTorch examplesLessons on explainability (SHAP, Grad-CAM), transfer learning, tabular data, time series, and working with real-world constraintsA closing roadmap for becoming a deep learning engineer who can ship systemsEach lesson is concise - filled with illustrations, examples, and engineering principles designed to build real intuition.Bonus: This book also serves as the official companion to the ArtificialGate course platform, used by enterprise teams and academic programs worldwide. All content is designed to support learners across technical backgrounds, and available in multiple languages.", "item_img_path" : "https://covers3.booksamillion.com/covers/bam/9/79/829/615/9798296157126_b.jpg", "price_data" : { "retail_price" : "26.00", "online_price" : "26.00", "our_price" : "26.00", "club_price" : "26.00", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }
Modern Deep Learning Foundation|Barak Or

Modern Deep Learning Foundation : From Fundamentals to Deployment - A Practical Guide for Engineers (2025)

local_shippingShip to Me
In Stock.
FREE Shipping for Club Members help

Overview

This is not just another deep learning book. Modern Deep Learning Foundations is a complete, hands-on guide for building, training, and deploying neural networks - written specifically for engineers who care about real-world systems, not just theoretical results.

Dr. Barak Or is an AI researcher, entrepreneur, and educator, with a PhD in ML for navigation systems, and a professional background that spans startups, deeptech technologies, and teaching at the Google-Reichman Tech School. He holds dual degrees in aeronautical engineering and economics & management from the Technion and has trained thousands of engineers across domains.

What's Inside:

  • Clear explanations of modern architectures: CNNs, RNNs, LSTMs, Transformers, Autoencoders, and more

  • In-depth coverage of training essentials: loss functions, backpropagation, optimization (AdamW, Lion, Adafactor), mixed precision, and regularization

  • Practical tools for industrial use: saving and versioning models, serving with FastAPI, and deploying to the cloud with full PyTorch examples

  • Lessons on explainability (SHAP, Grad-CAM), transfer learning, tabular data, time series, and working with real-world constraints

  • A closing roadmap for becoming a deep learning engineer who can ship systems

Each lesson is concise - filled with illustrations, examples, and engineering principles designed to build real intuition.

Bonus: This book also serves as the official companion to the ArtificialGate course platform, used by enterprise teams and academic programs worldwide. All content is designed to support learners across technical backgrounds, and available in multiple languages.

This item is Non-Returnable

Details

  • ISBN-13: 9798296157126
  • ISBN-10: 9798296157126
  • Publisher: Independently Published
  • Publish Date: August 2025
  • Dimensions: 9 x 6 x 0.38 inches
  • Shipping Weight: 0.62 pounds
  • Page Count: 146

Related Categories

You May Also Like...

    1

BAM Customer Reviews