KIP-Veröffentlichungen

Jahr 2018
Autor(en) Syed Ahmed Aamir*, Yannik Stradmann*, Paul Müller, Christian Pehle, Andreas Hartel, Andreas Grübl, Johannes Schemmel and Karlheinz Meier
Titel An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture
KIP-Nummer HD-KIP 18-40
KIP-Gruppe(n) F9
Dokumentart Paper
Keywords (angezeigt) Analog integrated circuits, Neuromorphic, Leaky Integrate and Fire, 65nm CMOS, Spiking neuron, OTA, Opamp, Tunable resistor, Winner-take-all network
Quelle IEEE Transactions on Circuits and Systems I: Regular Papers
Abstract (en)

Here we present an array of leaky integrate-and-fire (LIF) neuron circuits designed for the second-generation BrainScaleS mixed-signal 65-nm CMOS neuromorphic hardware. The neuronal array is embedded in the analog network core of a scaled-down prototype HICANN-DLS chip. Designed as continuous-time circuits, the neurons are highly tunable and reconfigurable elements with accelerated dynamics. Each neuron integrates input current from a multitude of incoming synapses and evokes a digital spike event output. The circuit offers a wide tuning range for synaptic and membrane time constants, as well as for refractory periods to cover a number of computational models. We elucidate our design methodology, underlying circuit design, calibration and measurement results from individual sub-circuits across multiple dies. The circuit dynamics match with the behavior of the LIF mathematical model. We further demonstrate a winner-take-all network on the prototype chip as a typical element of cortical processing.

Beispielbild
URL pdf
URL arXiv pre-print
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg