Kirjahaku
Etsi kirjoja tekijän nimen, kirjan nimen tai ISBN:n perusteella.
1000 tulosta hakusanalla Max Well
Etude de la convection naturelle turbulente
Max-Well Tientcheu Nsiewe
Editions Universitaires Europeennes
2020
pokkari
Nous avons men des investigations num riques sur l' tude de la convection naturelle turbulente dans une cavit carr e paroi diff rentiellement chauff e, dans laquelle nous soumettons une diff rence de temp rature de 10 K entre les parois verticales actives correspondant une valeur caract ristique du nombre de Rayleight de 107. Le model de turbulence κ-ε standard est utilis pour la r solution des quations math matique de Navier-Stokes a deux dimensions avec la moyenne de Reynolds (RANS), discr tis au second ordre Upwind scheme . L'algorithme SIMPLE d velopp , utilise la m thode des volumes finis pour la r solution num rique. Nous effectuons donc des calculs pour plusieurs valeurs du nombre de Rayleigh correspondant diff rents coulements et temp rature de parois. Les r sultats montrent que, en augmentant le nombre de Rayleigh, la distribution de temp rature et de vitesse ont des valeurs tr s lev l'entr e de la cavit . Les r sultats que nous obtenons, montrent suffisance le caract re turbulent et instable de l' coulement dans une enceinte ou un local chauff . La diff rence de temp rature tant le moteur.
Die pneumatische Schule bis auf Archigenes - in ihrer Entwicklung dargestellt
Max Wellmann
Severus
2011
pokkari
An Introduction to Variational Autoencoders
Diederik P. Kingma; Max Welling
now publishers Inc
2019
nidottu
In this monograph, the authors present an introduction to the framework of variational autoencoders (VAEs) that provides a principled method for jointly learning deep latent-variable models and corresponding inference models using stochastic gradient descent. The framework has a wide array of applications from generative modeling, semi-supervised learning to representation learning.The authors expand earlier work and provide the reader with the fine detail on the important topics giving deep insight into the subject for the expert and student alike. Written in a survey-like nature the text serves as a review for those wishing to quickly deepen their knowledge of the topic.An Introduction to Variational Autoencoders provides a quick summary for the of a topic that has become an important tool in modern-day deep learning techniques.
Structured Representation Learning
Yue Song; Thomas Anderson Keller; Nicu Sebe; Max Welling
Springer International Publishing AG
2025
sidottu
This book introduces approaches to generalize the benefits of equivariant deep learning to a broader set of learned structures through learned homomorphisms. In the field of machine learning, the idea of incorporating knowledge of data symmetries into artificial neural networks is known as equivariant deep learning and has led to the development of cutting edge architectures for image and physical data processing. The power of these models originates from data-specific structures ingrained in them through careful engineering. To-date however, the ability for practitioners to build such a structure into models is limited to situations where the data must exactly obey specific mathematical symmetries. The authors discuss naturally inspired inductive biases, specifically those which may provide types of efficiency and generalization benefits through what are known as homomorphic representations, a new general type of structured representation inspired from techniques in physics and neuroscience. A review of some of the first attempts at building models with learned homomorphic representations are introduced. The authors demonstrate that these inductive biases improve the ability of models to represent natural transformations and ultimately pave the way to the future of efficient and effective artificial neural networks.
Equivariant And Coordinate Independent Convolutional Networks: A Gauge Field Theory Of Neural Networks
Patrick Forre; Erik Verlinde; Maurice Weiler; Max Welling
WORLD SCIENTIFIC PUBLISHING CO PTE LTD
2025
sidottu
What is the appropriate geometric structure for neural networks for processing spatial signals like images, point clouds, or tensor fields? This question takes us on a journey towards a gauge field theory of convolutional neural networks.A considerable part of machine learning applications is concerned with analyzing fields of feature vectors on Euclidean spaces or more general manifolds. Model predictions should thereby remain consistent when applying geometric transformations to the fields or the coordinate systems describing them. This book derives and characterizes the implied symmetry constraints on thus defined equivariant convolutional neural networks. Instead of focusing on one specific setting, it develops a general representation theoretic formulation for arbitrary symmetry groups and spaces. The theory is made concrete in several chapters discussing implementations of equivariant convolutional networks on various manifolds.This monograph is essential reading for anyone interested in signal processing in the presence of symmetries. It is relevant for any applications where patterns appear in various geometric poses, including, for instance, medical and satellite imaging, molecule generation, or climate modeling.
