Deep Neural Network Feasibility Using Analog Spiking Neurons

Thomas Soupizet (1) , Zalfa Jouni (1) , Joao Frischenbruder Sulzbach (1) , A. Benlarbi-Delai (1) , Pietro Maris Ferreira (1)

1 GeePs - Laboratoire Génie électrique et électronique de Paris

Novel non-Von-Neumann solutions have raised based on artificial intelligence (AI) such as the neuromorphic spiking processors in either analog or digital domain. This paper proposes to study the deep neural network feasibility using ultra-low-power eNeuron. The trade-offs in terms of deep learning capabilities and energy efficiency are highlighted. A linear fit model is found in the region of high energy efficiency of neuromorphic components. Thus, deep learning and energy efficiency mutually exclusive if those neuromorphic components are used.

Keywords: neuromorphic circuits; spiking neural network; deep learning; low power

Domains: Micro and nanotechnologies/Microelectronics; Electronics

Thomas Soupizet, Zalfa Jouni, Joao Frischenbruder Sulzbach, A. Benlarbi-Delai, Pietro Maris Ferreira. Deep Neural Network Feasibility Using Analog Spiking Neurons. 35th SBC/SBMicro/IEEE/ACM Symposium on Integrated Circuits and Systems Design (SBCCI), Aug 2022, Porto Alegre, Brazil. ⟨10.1109/SBCCI55532.2022.9893216⟩. ⟨hal-03689837⟩