Results 81 to 90 of about 71,359 (311)
Reinforcement Learning with Function Approximation: From Linear to Nonlinear [PDF]
Jihao Long, Jiequn Han
openalex +1 more source
Nonlinear Approximation and (Deep) ReLU Networks
This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural networks approximate functions with classical smoothness to the same accuracy as classical linear methods of ...
Ingrid Daubechies +4 more
openaire +2 more sources
Soft Mechanical‐Electrical Logic Using Liquid Metal‐Filled 3D‐Printed Architectures
We present 3D‐printed soft mechanical–electrical logic elements that use liquid metal–filled silicone tubes actuated by thermoplastic polyurethane/polylactic acid (TPU/PLA) architectures to produce Boolean operations. Complementary normally open and normally closed unit cells perform repeatable binary transitions and can be combined into more complex ...
Christoph Lehmann +2 more
wiley +1 more source
Approximation of derivatives by nonlinear operators
Two theorems on simultaneous approximation are obtained by using generalized convex operators.
Radu Păltănea
doaj +2 more sources
Incomplete Phase Space Reconstruction Method Based on Subspace Adaptive Evolution Approximation
The chaotic time series can be expanded to the multidimensional space by phase space reconstruction, in order to reconstruct the dynamic characteristics of the original system.
Tai-fu Li +5 more
doaj +1 more source
Coarse‐grained (left) and atomistic (right) models of the shape memory polymer ESTANE ETE 75DT3 are shown schematically. The two representations bridge molecular detail and mesoscopic description. Both models capture shape memory behavior, linking segmental mobility and conformational relaxation of anisotropic chains to macroscopic recovery, and ...
Fathollah Varnik
wiley +1 more source
An implementable nonlinear Lagrange algorithm for stochastic minimax problems is presented based on sample average approximation method in this paper, in which the second step minimizes a nonlinear Lagrange function with sample average approximation ...
Suxiang He, Yunyun Nie, Xiaopeng Wang
doaj +1 more source
Predistortion Approaches Using Coefficient Approximation and Bidirectional LSTM for Nonlinearity Compensation in Visible Light Communication [PDF]
Yun-Joong Park +2 more
openalex +1 more source
This study shows that superalloys used in aircraft engine disks become much more prone to deformation at high temperatures if they have been strained during manufacturing. This effect increases with the level of prior strain but eventually reaches a limit.
Fabio Machado Alves da Fonseca +9 more
wiley +1 more source
Motivated by important applications to the analysis of complex noise-induced phenomena, we consider a problem of the constructive description of randomly forced equilibria for nonlinear systems with multiplicative noise.
Irina Bashkirtseva
doaj +1 more source

