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

TL;DR

This paper introduces Neural Network Processing Neural Networks (NNPNNs), a novel neural network class that processes other neural networks and numerical data, enhancing the ability to represent and manipulate complex structures.

Contribution

The paper presents a new neural network architecture that processes neural networks as inputs, enabling richer structure representation and processing capabilities.

Findings

NNPNNs can represent complex structures more effectively.

The proposed method extends neural network capabilities to higher-order functions.

Potential applications include advanced data processing and structural understanding.

Abstract

Functions are rich in meaning and can be interpreted in a variety of ways. Neural networks were proven to be capable of approximating a large class of functions[1]. In this paper, we propose a new class of neural networks called "Neural Network Processing Neural Networks" (NNPNNs), which inputs neural networks and numerical values, instead of just numerical values. Thus enabling neural networks to represent and process rich structures.