Results 11 to 20 of about 66,291 (256)
On sharpness of error bounds for multivariate neural network approximation [PDF]
Ricerche di Matematica, 2020 AbstractSingle hidden layer feedforward neural networks can represent multivariate functions that are sums of ridge functions. These ridge functions are defined via an activation function and customizable weights. The paper deals with best non-linear approximation by such sums of ridge functions.
openaire +3 more sources
IEEE Access, 2023 Locomotive traction energy consumption is a multivariate coupled nonlinear system closely related to many factors such as locomotive properties, routing, line conditions, and operating methods.
Huize Liang +4 more
doaj +1 more source
Journal of Control Science and Engineering, 2022 In order to solve the problem that the traditional long-term high-speed traffic forecasting algorithm is affected by the approximation ability of the function and easy to fall into the local mass value, we wrote a multivariate-based highway traffic ...
Yuzhu Luo, Jiarong Wang, Ming Wei
doaj +1 more source
Improved Uncertainty Quantification for Neural Networks With Bayesian Last Layer
IEEE Access, 2023 Uncertainty quantification is an important task in machine learning - a task in which standard neural networks (NNs) have traditionally not excelled. This can be a limitation for safety-critical applications, where uncertainty-aware methods like Gaussian
Felix Fiedler, Sergio Lucia
doaj +1 more source
A Neural Network Approximation Based on a Parametric Sigmoidal Function
Mathematics, 2019 It is well known that feed-forward neural networks can be used for approximation to functions based on an appropriate activation function. In this paper, employing a new sigmoidal function with a parameter for an activation function, we consider a ...
Beong In Yun
doaj +1 more source
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review [PDF]
, 2017 The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential
Liao, Qianli +4 more
core +6 more sources
Machine Learning Alternatives to Response Surface Models
Mathematics, 2023 In the Design of Experiments, we seek to relate response variables to explanatory factors. Response Surface methodology (RSM) approximates the relation between output variables and a polynomial transform of the explanatory variables using a linear model.
Badih Ghattas, Diane Manzon
doaj +1 more source
A Coverage Study of the CMSSM Based on ATLAS Sensitivity Using Fast Neural Networks Techniques [PDF]
, 2011 We assess the coverage properties of confidence and credible intervals on the CMSSM parameter space inferred from a Bayesian posterior and the profile likelihood based on an ATLAS sensitivity study.
Bridges, M. +5 more
core +2 more sources
IEEE Access, 2023 We analyze a fixed-point algorithm for reinforcement learning (RL) of optimal portfolio mean-variance preferences in the setting of multivariate generalized autoregressive conditional-heteroskedasticity (MGARCH) with a small penalty on trading.
Andrew Papanicolaou +3 more
doaj +1 more source
European Physical Journal C: Particles and Fields, 2022 We present the novel implementation of a non-differentiable metric approximation and a corresponding loss-scheduling aimed at the search for new particles of unknown mass in high energy physics experiments.
F. Abudinén +45 more
doaj +1 more source