“…For artificial neural networks (ANNs), these techniques span from simplifying models, such as pruning and quantization (Han et al, 2015;Wen et al, 2016;Yang et al, 2018;Zoph et al, 2018), to designing energy efficient architectures (Jin et al, 2014;Panda et al, 2016;Parsa et al, 2017;Wang et al, 2017), and neural architecture search (Zoph et al, 2018). In spiking neuromorphic domain, these include different training algorithms such as Schuman et al (2016), Bohnstingl et al (2019) based on evolutionary optimization, Esser et al (2015Esser et al ( , 2016 on modified backpropagation techniques, Severa et al (2019) as binary communication, and Rathi et al (2020) as a hybrid approach and then deploying these on neuromorphic hardware such as Schmitt et al (2017) and Koo et al (2020). In this section, we briefly introduce each of these methods and continue with the added complexity of co-designing hardware and software for artificial neural networks and spiking neuromorphic systems.…”