Some negative results for Neural Networks

10/23/2018
by   J. M. Almira, et al.
1

We demonstrate some negative results for approximation of functions with neural networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/29/2019

Approximation of functions by neural networks

We study the approximation of measurable functions on the hypercube by f...
research
08/14/2021

Optimal Approximation with Sparse Neural Networks and Applications

We use deep sparsely connected neural networks to measure the complexity...
research
11/06/2019

Neural Network Processing Neural Networks: An efficient way to learn higher order functions

Functions are rich in meaning and can be interpreted in a variety of way...
research
06/10/2023

Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem

Injective multiset functions have a key role in the theoretical study of...
research
08/05/2022

Why do networks have inhibitory/negative connections?

Why do brains have inhibitory connections? Why do deep networks have neg...
research
10/26/2022

Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation

Since batch algorithms suffer from lack of proficiency in confronting mo...
research
09/18/2018

Negative type diversities, a multi-dimensional analogue of negative type metrics

Diversities are a generalization of metric spaces in which a non-negativ...

Please sign up or login with your details

Forgot password? Click here to reset