Mathematical Theory of Deep Learning: A Gentle but Rigorous Audio Guide to the Foundations Behind Modern Neural Networks
カートのアイテムが多すぎます
カートに追加できませんでした。
ウィッシュリストに追加できませんでした。
ほしい物リストの削除に失敗しました。
ポッドキャストのフォローに失敗しました
ポッドキャストのフォロー解除に失敗しました
聴き放題対象外タイトルです。Audibleプレミアムプラン登録で、非会員価格の30%OFFで購入できます。
¥1,260 で購入
-
ナレーター:
-
Virtual Voice
-
著者:
-
Michael Hartmann
この作品は、デジタルボイスによる朗読を使用しています。
Master the mathematics of artificial intelligence and turn deep learning algorithms into crystal-clear mental models. Whether you are upskilling during your morning commute or diving into a focused study session, this enlightening audio journey replaces dense coding tutorials with intuitive logic. Grasp the true mechanics behind the code using nothing but your mind and fundamental linear algebra.
Escape the frustration of black-box systems by visualizing the geometry of high-dimensional spaces and the exact training dynamics driving modern tech. This rigorous yet highly accessible experience empowers analytical thinkers to internalize high-level proofs and optimization strategies on the go.
What you'll discover inside:
• The precise mathematical mechanics governing linear models, capacity, and algorithmic generalization.
• Intuitive, verbal proofs that translate dense formulas into vivid mental pictures you can follow anywhere.
• How depth, width, and architectural choices act as levers to shape what neural networks can truly represent.
• The hidden structures behind convolutional and attention-based systems, decoded as pure mathematical logic.
• A comprehensive breakdown of the tension between data capacity and finding simple explanations within large parameters.
• Emerging open problems in the tech landscape and what they reveal about the next generation of machine learning.
Stop simply running code and start comprehending the brilliant mathematical architecture that makes it work. Equip yourself with the conceptual framework needed to parse new theoretical breakthroughs and stay ahead of the curve. Hit play now to build a lasting, rigorous intuition for the future of technology.
©2026 Hidden Voices (P)2026 Hidden Voices