From Convolutions towards Spikes: The Environmental Metric that the Community currently Misses

TL;DR

This paper emphasizes the importance of environmental metrics in AI, advocates for spike-based neural networks and neuromorphic hardware for energy efficiency, and introduces the 'NATURE' metric to assess carbon footprint.

Contribution

It highlights the environmental impact of AI, advocates for neuromorphic computing, and proposes a new metric 'NATURE' for carbon footprint evaluation.

Findings

Current ANNs are not biologically inspired.

Spiking neural networks are more energy-efficient but underexplored.

Introduction of the 'NATURE' metric for environmental assessment.

Abstract

Today, the AI community is obsessed with 'state-of-the-art' scores (80% papers in NeurIPS) as the major performance metrics, due to which an important parameter, i.e., the environmental metric, remains unreported. Computational capabilities were a limiting factor a decade ago; however, in foreseeable future circumstances, the challenge will be to develop environment-friendly and power-efficient algorithms. The human brain, which has been optimizing itself for almost a million years, consumes the same amount of power as a typical laptop. Therefore, developing nature-inspired algorithms is one solution to it. In this study, we show that currently used ANNs are not what we find in nature, and why, although having lower performance, spiking neural networks, which mirror the mammalian visual cortex, have attracted much interest. We further highlight the hardware gaps restricting the researchers from using spike-based computation for developing neuromorphic energy-efficient microchips on a large scale. Using neuromorphic processors instead of traditional GPUs might be more environment friendly and efficient. These processors will turn SNNs into an ideal solution for the problem. This paper presents in-depth attention highlighting the current gaps, the lack of comparative research, while proposing new research directions at the intersection of two fields -- neuroscience and deep learning. Further, we define a new evaluation metric 'NATURE' for reporting the carbon footprint of AI models.