Mathematics and Deep Learning Architecture

Mathematics and Deep Learning Architecture

Discover what happens inside the black box! To use deep learning, you will need to prepare data, choose the right model, train it, evaluate quality and accuracy, and account for uncertainty and variability in the output of the deployed solution.... This book introduces you step by step to the fundamental mathematical concepts that will be useful to you as a data specialist, - including vector calculus, linear algebra, and Bayesian inference, presenting them from the perspective of deep learning.
The authors explain the mathematics, theory, and principles of building deep learning models, and then demonstrate the application of theory in practice, providing snippets of Python code with detailed comments. In this book, you will journey from the basics of algebra, calculus, and statistics to modern deep learning architectures that have emerged from the latest research.

1. The book introduces the fundamental mathematical concepts step by step that will be useful to you as a data specialist.
2. Key principles of neural network design.
3. Implementation of deep learning in Python using PyTorch.
4. Regularization and optimization of inefficient models.
5. Discover what happens inside the black box!

Printhouse: piter

Series: Programmer's Library

Age restrictions: 16+

Year of publication: 2025

ISBN: 9785446141678

Number of pages: 576

Size: 233х165х30 mm

Cover type: soft

Weight: 889 g

ID: 1721924

Discover what happens inside the black box! To use deep learning, you will need to prepare data, choose the right model, train it, evaluate quality and accuracy, and account for uncertainty and variability in the output of the deployed solution. This book introduces you step by step to the fundamental mathematical concepts that will be useful to you as a data specialist, - including vector calculus, linear algebra, and Bayesian inference, presenting them from the perspective of deep learning.
The authors explain the mathematics, theory, and principles of building deep learning models, and then demonstrate the application of theory in practice, providing snippets of Python code with detailed comments. In this book, you will journey from the basics of algebra, calculus, and statistics to modern deep learning architectures that have emerged from the latest research.

1. The book introduces the fundamental mathematical concepts step by step that will be useful to you as a data specialist.
2. Key principles of neural network design.
3. Implementation of deep learning in Python using PyTorch.
4. Regularization and optimization of inefficient models.
5. Discover what happens inside the black box!