Neural Networks, Hypersurfaces, and Radon Transforms

07/04/2019
by   Soheil Kolouri, et al.
6

Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks. By analyzing the properties of neural networks as operators on probability distributions for observed data, we show that the distribution of outputs for any node in a neural network can be interpreted as a nonlinear projection along hypersurfaces defined by level surfaces over the input data space. We utilize these descriptions to provide new interpretation for phenomena such as nonlinearity, pooling, activation functions, and adversarial examples in neural network-based learning problems.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

research
07/23/2020

The Representation Theory of Neural Networks

In this work, we show that neural networks can be represented via the ma...
research
07/26/2023

Fixed Integral Neural Networks

It is often useful to perform integration over learned functions represe...
research
02/09/2022

A Local Geometric Interpretation of Feature Extraction in Deep Feedforward Neural Networks

In this paper, we present a local geometric analysis to interpret how de...
research
07/13/2022

MorphoActivation: Generalizing ReLU activation function by mathematical morphology

This paper analyses both nonlinear activation functions and spatial max-...
research
10/05/2019

Minimum "Norm" Neural Networks are Splines

We develop a general framework based on splines to understand the interp...
research
03/27/2019

Neural-networks for geophysicists and their application to seismic data interpretation

Neural-networks have seen a surge of interest for the interpretation of ...
research
01/31/2019

Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints

In this paper, we introduce a novel concept for learning of the paramete...

Please sign up or login with your details

Forgot password? Click here to reset