Porting HTM Models to the Heidelberg Neuromorphic Computing Platform
This work addresses the challenge of running large-scale HTM networks efficiently on neuromorphic hardware, which could benefit researchers in neuromorphic computing and machine intelligence, though it is incremental as it builds on existing HTM and platform technologies.
The researchers tackled the problem of implementing Hierarchical Temporal Memory (HTM) models on the Heidelberg Neuromorphic Computing Platform by developing a framework for simulating key HTM operations with spiking networks, demonstrating that fundamental properties are maintained in initial simulations.
Hierarchical Temporal Memory (HTM) is a computational theory of machine intelligence based on a detailed study of the neocortex. The Heidelberg Neuromorphic Computing Platform, developed as part of the Human Brain Project (HBP), is a mixed-signal (analog and digital) large-scale platform for modeling networks of spiking neurons. In this paper we present the first effort in porting HTM networks to this platform. We describe a framework for simulating key HTM operations using spiking network models. We then describe specific spatial pooling and temporal memory implementations, as well as simulations demonstrating that the fundamental properties are maintained. We discuss issues in implementing the full set of plasticity rules using Spike-Timing Dependent Plasticity (STDP), and rough place and route calculations. Although further work is required, our initial studies indicate that it should be possible to run large-scale HTM networks (including plasticity rules) efficiently on the Heidelberg platform. More generally the exercise of porting high level HTM algorithms to biophysical neuron models promises to be a fruitful area of investigation for future studies.