Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

Abstract

a b s t r a c tThe application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks.

Classification and regression of spatio-temporal signals using NeuCube and its realization on SpiNNaker neuromorphic hardware

“…With this regard, one appropriate future test would be to use the hybrid-brain-computer interface (hBCI) by combining EEG and sEMG [61], which may further validate this implementation. Additionally, it is important to highlight that since we have used PyNN [52], the same implementation should run on other contemporary and future neuromorphic and neuroinspired hardware platforms [62,63]. Last, as was shown previously in Section 1.1.2, the huge number of applications where NeuCube could be used as well as the versatility of such a model could make our proposed approach applicable across different domains.…”

Unsupervised heart-rate estimation in wearables with Liquid states and a probabilistic readout

“…Advancing neuromorphic computing: Neuromorphic computing has matured significantly in recent years. This growth is fueled by innovations in materials [84,85,86], circuits [64,87,88,89], algorithms [90,91,92] and applications [55,93,94]. Our work falls in the interface between neuromorphic applications and algorithms.…”

Behavioral Learning in a Cognitive Neuromorphic Robot: An Integrative Approach

“…At least in principle, spiking neural networks seem to be able to solve difficult cognitive problems [10] in possibly nonstationary environments [11]. This could inform both neuroscience and robotics [12], however, contrasting priorities between the two communities have created a lack of clarity over what aspects of neural modeling are most meaningful, limiting progress in neurorobotics.…”

“…But, a new large-scale generation can credibly implement entire cognitive systems, either in fixed-model analog chips [38] or programmable architectures that can simulate multiple models [39], [40]. Both styles of design emphasize significantly lower power consumption [41], [42] and improved real-time response [17], and feature a variety of learning implementations [12] (not necessarily on-line or on-chip [40]).…”