Super Neurons

TL;DR

This paper introduces super neurons that enable neural networks to have larger receptive fields through learnable or random kernel shifts, improving learning and generalization without increasing complexity.

Contribution

It proposes novel super neuron models with non-localized kernel operations, enhancing receptive fields in Self-ONNs.

Findings

Super neurons increase receptive field size effectively.

They improve learning and generalization capabilities.

They maintain minimal computational complexity.

Abstract

Self-Organized Operational Neural Networks (Self-ONNs) have recently been proposed as new-generation neural network models with nonlinear learning units, i.e., the generative neurons that yield an elegant level of diversity; however, like its predecessor, conventional Convolutional Neural Networks (CNNs), they still have a common drawback: localized (fixed) kernel operations. This severely limits the receptive field and information flow between layers and thus brings the necessity for deep and complex models. It is highly desired to improve the receptive field size without increasing the kernel dimensions. This requires a significant upgrade over the generative neurons to achieve the non-localized kernel operations for each connection between consecutive layers. In this article, we present superior (generative) neuron models (or super neurons in short) that allow random or learnable kernel shifts and thus can increase the receptive field size of each connection. The kernel localization process varies among the two super-neuron models. The first model assumes randomly localized kernels within a range and the second one learns (optimizes) the kernel locations during training. An extensive set of comparative evaluations against conventional and deformable convolutional, along with the generative neurons demonstrates that super neurons can empower Self-ONNs to achieve a superior learning and generalization capability with a minimal computational complexity burden.