Zobrazeno 1 - 10
of 5 054
pro vyhledávání: '"universal approximation theorem"'
Autor:
Ismailov, Vugar
We study feedforward neural networks with inputs from a topological vector space (TVS-FNNs). Unlike traditional feedforward neural networks, TVS-FNNs can process a broader range of inputs, including sequences, matrices, functions and more. We prove a
Externí odkaz:
http://arxiv.org/abs/2409.12913
Autor:
Monico, Chris
In this short note, we give an elementary proof of a universal approximation theorem for neural networks with three hidden layers and increasing, continuous, bounded activation function. The result is weaker than the best known results, but the proof
Externí odkaz:
http://arxiv.org/abs/2406.10002
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Scellier, Benjamin, Mishra, Siddhartha
Resistor networks have recently attracted interest as analog computing platforms for machine learning, particularly due to their compatibility with the Equilibrium Propagation training framework. In this work, we explore the computational capabilitie
Externí odkaz:
http://arxiv.org/abs/2312.15063
Autor:
Gonon, Lukas, Jacquier, Antoine
Universal approximation theorems are the foundations of classical neural networks, providing theoretical guarantees that the latter are able to approximate maps of interest. Recent results have shown that this can also be achieved in a quantum settin
Externí odkaz:
http://arxiv.org/abs/2307.12904
Publikováno v:
Intelligent Systems. BRACIS 2022. Lecture Notes in Computer Science, vol 13654
The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the use of neur
Externí odkaz:
http://arxiv.org/abs/2209.02456
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Voigtlaender, Felix
Publikováno v:
In Applied and Computational Harmonic Analysis May 2023 64:33-61
Autor:
Nishijima, Takato
Is there any theoretical guarantee for the approximation ability of neural networks? The answer to this question is the "Universal Approximation Theorem for Neural Networks". This theorem states that a neural network is dense in a certain function sp
Externí odkaz:
http://arxiv.org/abs/2102.10993
Autor:
Wang, Ji-Yuan, Pan, Xiao-Min
Publikováno v:
IEEE Transactions on Antennas and Propagation; December 2024, Vol. 72 Issue: 12 p9274-9285, 12p