menu
{ "item_title" : "Mathematical Foundations and Transformer Principles", "item_author" : [" Wei Sun "], "item_description" : "The Transformer Principles Series is a three-volume graduate-level treatise that builds a complete mathematical and engineering understanding of modern AI systems, from the foundational attention mechanism to large language models and multimodal architectures. Volume I - Mathematical Foundations and Transformer Principles begins with the historical evolution from symbolic AI to deep learning, then develops the essential mathematics: linear algebra, probability, optimization, neural network backpropagation, and information theory. These tools are applied through a systematic construction of the Transformer - self-attention, multi-head projections, positional encodings, feed-forward networks, residual connections, and normalization - culminating in the complete encoder-decoder architecture and an exploration of efficient attention variants, mixture-of-experts, and state-space models.", "item_img_path" : "https://covers3.booksamillion.com/covers/bam/9/79/818/209/9798182096218_b.jpg", "price_data" : { "retail_price" : "79.99", "online_price" : "79.99", "our_price" : "79.99", "club_price" : "79.99", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }
Mathematical Foundations and Transformer Principles|Wei Sun

Mathematical Foundations and Transformer Principles

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

Overview

The Transformer Principles Series is a three-volume graduate-level treatise that builds a complete mathematical and engineering understanding of modern AI systems, from the foundational attention mechanism to large language models and multimodal architectures. Volume I - Mathematical Foundations and Transformer Principles begins with the historical evolution from symbolic AI to deep learning, then develops the essential mathematics: linear algebra, probability, optimization, neural network backpropagation, and information theory. These tools are applied through a systematic construction of the Transformer - self-attention, multi-head projections, positional encodings, feed-forward networks, residual connections, and normalization - culminating in the complete encoder-decoder architecture and an exploration of efficient attention variants, mixture-of-experts, and state-space models.

This item is Non-Returnable

Details

  • ISBN-13: 9798182096218
  • ISBN-10: 9798182096218
  • Publisher: Independently Published
  • Publish Date: June 2026
  • Dimensions: 11 x 8.5 x 1.11 inches
  • Shipping Weight: 2.77 pounds
  • Page Count: 550

Related Categories

You May Also Like...

    1

BAM Customer Reviews