Circuits and Systems for a Spiking Neuromorphic Network in 28 nm CMOS

Circuits and Systems for a Spiking Neuromorphic Network in 28 nm CMOS

Hettema, Bart (TU Delft Electrical Engineering, Mathematics and Computer Science)

van Leuken, T.G.R.M. (mentor)
Zjajo, Amir (graduation committee)
Bishnoi, R.K. (graduation committee)

Delft University of Technology

Electrical Engineering | Circuits and Systems

2024-02-06

Neuromorphic computing can be used to efficiently implement spiking neural networks.
Such spiking neural networks can be used in edge AI applications, where low power consumption is paramount.
The use of analog components allows for extremely low power implementations.
This thesis contributes the designs of an analog spike generator, synaptic elements and an accumulating neuron in 28 nm CMOS technology.
The elements are assembled in a neural network and laid out in an SoC.
Energy consumption numbers of less than 1 pJ/synaptic operation are achieved in the analog neuromorphic components.

neuromorphic computing
spiking neural network
neuron
synapse
CMOS

http://resolver.tudelft.nl/uuid:001ae989-286d-4c5c-8976-be08ef46b71b

Student theses

master thesis

© 2024 Bart Hettema