COMPUTATION COMPLEXITY OF DEEP RELU NEURAL NETWORKS IN HIGH-DIMENSIONAL APPROXIMATION
نویسندگان
چکیده
The purpose of the present paper is to study computation complexity deep ReLU neural networks approximate functions in H\"older-Nikol'skii spaces mixed smoothness $H_\infty^\alpha(\mathbb{I}^d)$ on unit cube $\mathbb{I}^d:=[0,1]^d$. In this context, for any function $f\in H_\infty^\alpha(\mathbb{I}^d)$, we explicitly construct nonadaptive and adaptive having an output that approximates $f$ with a prescribed accuracy $\varepsilon$, prove dimension-dependent bounds approximation, characterized by size depth network, $d$ $\varepsilon$. Our results show advantage method approximation over one.
منابع مشابه
Optimal approximation of continuous functions by very deep ReLU networks
We prove that deep ReLU neural networks with conventional fully-connected architectures with W weights can approximate continuous ν-variate functions f with uniform error not exceeding aνωf (cνW −2/ν), where ωf is the modulus of continuity of f and aν , cν are some ν-dependent constants. This bound is tight. Our construction is inherently deep and nonlinear: the obtained approximation rate cann...
متن کاملOptimal approximation of piecewise smooth functions using deep ReLU neural networks
We study the necessary and sufficient complexity of ReLU neural networks—in terms of depth and number of weights—which is required for approximating classifier functions in an L-sense. As a model class, we consider the set E(R) of possibly discontinuous piecewise C functions f : [−1/2, 1/2] → R, where the different “smooth regions” of f are separated by C hypersurfaces. For given dimension d ≥ ...
متن کاملNonparametric regression using deep neural networks with ReLU activation function
Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to log n-factors) under a general composition assumption on the regression function. The framework includes many well-studied structural constrain...
متن کاملDropout Rademacher Complexity Of Deep Neural Networks
Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed; however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of featur...
متن کاملProvable approximation properties for deep neural networks
We discuss approximation of functions using deep neural nets. Given a function f on a d-dimensional manifold Γ ⊂ R, we construct a sparsely-connected depth-4 neural network and bound its error in approximating f . The size of the network depends on dimension and curvature of the manifold Γ, the complexity of f , in terms of its wavelet description, and only weakly on the ambient dimension m. Es...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Computer Science and Cybernetics
سال: 2021
ISSN: ['1813-9663']
DOI: https://doi.org/10.15625/1813-9663/37/3/15902