Name: Pdes, Control and Deep Learning: Cetraro, Italy 2024 (en Inglés)
SKU: 66919798
Price: 90.42 USD
Availability: InStock
Author: Coclite, Giuseppe; Zuazua, Enrique; Bressan, Alberto
ISBN: 9783032187420

portada Pdes, Control and Deep Learning: Cetraro, Italy 2024 (en Inglés)

Pdes, Control and Deep Learning: Cetraro, Italy 2024 (en Inglés)

Formato

Libro Físico

Editorial

Springer

Autor

Coclite, Giuseppe; Zuazua, Enrique; Bressan, Alberto

Idioma

Inglés

N° páginas

112

Encuadernación

Tapa Blanda

ISBN13

9783032187420

Pdes, Control and Deep Learning: Cetraro, Italy 2024 (en Inglés)

Coclite, Giuseppe; Zuazua, Enrique; Bressan, Alberto (Autor) · Springer · Tapa Blanda

Libro Nuevo Importado

Envío: 39 a 46 días háb.

$ 164.40$ 90.42

-45%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 20 unidades

$ 90.42

Llega entre el 26 Oct y el 10 Nov a Quito, Pichincha. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Pdes, Control and Deep Learning: Cetraro, Italy 2024 (en Inglés)"

This volume includes lectures presented at the CIME School on "PDEs, Control and Deep Learning", held in Cetraro (Italy) from July 22 to 26, 2024. It provides a comprehensive and up-to-date view of the diverse and rapidly evolving field of nonlinear partial differential equations (PDEs), with an emphasis on modeling, analysis, control, and deep learning aspects. The theory of PDEs interacts closely with almost all areas of physics and many branches of mathematics. As explicit solutions of PDEs are rarely available (except in the simplest cases), numerical approximations play a central role in their study. Machine learning, particularly through artificial neural networks, introduces powerful methods for function approximation through layered structures of interconnected units (neurons) that combine linear transformations and nonlinear activations. Deep learning (the use of neural networks with many hidden layers) has proven to be remarkably eﬀective in a wide range of applications. At the same time, recent advances in PDEs and control theory are beginning to inform machine learning, providing new theoretical perspectives. The book will be a valuable resource for PhD students and researchers seeking to deepen their understanding of partial differential equations, control, and their connections to modern machine learning.