Adaptive ‘life-long’ learning at the edge and during online task performance is an aspirational goal of artificial intelligence research. Neuromorphic hardware implementing spiking neural networks (SNNs) are particularly attractive in this regard, as their real-time, event-based, local computing paradigm makes them suitable for edge implementations and fast learning. However, the long and iterative learning that characterizes state-of-the-art SNN training is incompatible with the physical nature and real-time operation of neuromorphic hardware. Bi-level learning, such as meta-learning is increasingly used in deep learning to overcome these limitations. In this work, we demonstrate gradient-based meta-learning in SNNs using the surrogate gradient method that approximates the spiking threshold function for gradient estimations. Because surrogate gradients can be made twice differentiable, well-established, and effective second-order gradient meta-learning methods such as model agnostic meta learning (MAML) can be used. We show that SNNs meta-trained using MAML perform comparably to conventional artificial neural networks meta-trained with MAML on event-based meta-datasets. Furthermore, we demonstrate the specific advantages that accrue from meta-learning: fast learning without the requirement of high precision weights or gradients, training-to-learn with quantization and mitigating the effects of approximate synaptic plasticity rules. Our results emphasize how meta-learning techniques can become instrumental for deploying neuromorphic learning technologies on real-world problems.
Neuromorphic computing has the great potential to enable faster and more energy‐efficient computing by overcoming the von Neumann bottleneck. However, most emerging nonvolatile memory (NVM)‐based artificial synapses suffer from insufficient precision, nonlinear synaptic weight update, high write voltage, and high switching latency. Moreover, the spatiotemporal dynamics, an important temporal component for cognitive computing in spiking neural networks (SNNs), are hard to generate with existing complementary metal–oxide–semiconductor (CMOS) devices or emerging NVM. Herein, a three‐terminal, Li
- NSF-PAR ID:
- 10252076
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Advanced Intelligent Systems
- Volume:
- 3
- Issue:
- 9
- ISSN:
- 2640-4567
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
null (Ed.)Brain-inspired cognitive computing has so far followed two major approaches - one uses multi-layered artificial neural networks (ANNs) to perform pattern-recognition-related tasks, whereas the other uses spiking neural networks (SNNs) to emulate biological neurons in an attempt to be as efficient and fault-tolerant as the brain. While there has been considerable progress in the former area due to a combination of effective training algorithms and acceleration platforms, the latter is still in its infancy due to the lack of both. SNNs have a distinct advantage over their ANN counterparts in that they are capable of operating in an event-driven manner, thus consuming very low power. Several recent efforts have proposed various SNN hardware design alternatives, however, these designs still incur considerable energy overheads.In this context, this paper proposes a comprehensive design spanning across the device, circuit, architecture and algorithm levels to build an ultra low-power architecture for SNN and ANN inference. For this, we use spintronics-based magnetic tunnel junction (MTJ) devices that have been shown to function as both neuro-synaptic crossbars as well as thresholding neurons and can operate at ultra low voltage and current levels. Using this MTJ-based neuron model and synaptic connections, we design a low power chip that has the flexibility to be deployed for inference of SNNs, ANNs as well as a combination of SNN-ANN hybrid networks - a distinct advantage compared to prior works. We demonstrate the competitive performance and energy efficiency of the SNNs as well as hybrid models on a suite of workloads. Our evaluations show that the proposed design, NEBULA, is up to 7.9× more energy efficient than a state-of-the-art design, ISAAC, in the ANN mode. In the SNN mode, our design is about 45× more energy-efficient than a contemporary SNN architecture, INXS. Power comparison between NEBULA ANN and SNN modes indicates that the latter is at least 6.25× more power-efficient for the observed benchmarks.more » « less
-
Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors. However, existing SNN error backpropagation (BP) methods lack proper handling of spiking discontinuities and suffer from low performance compared with the BP methods for traditional artificial neural networks. In addition, a large number of time steps are typically required to achieve decent performance, leading to high latency and rendering spike based computation unscalable to deep architectures. We present a novel Temporal Spike Sequence Learning Backpropagation (TSSL-BP) method for training deep SNNs, which breaks down error backpropagation across two types of inter-neuron and intra-neuron dependencies and leads to improved temporal learning precision. It captures inter-neuron dependencies through presynaptic firing times by considering the all-or-none characteristics of firing activities, and captures intra-neuron dependencies by handling the internal evolution of each neuronal state in time. TSSL-BP efficiently trains deep SNNs within a much shortened temporal window of a few steps while improving the accuracy for various image classification datasets including CIFAR10.more » « less
-
more » « less
Abstract Memristors for neuromorphic computing have gained prominence over the years for implementing synapses and neurons due to their nano-scale footprint and reduced complexity. Several demonstrations show two-dimensional (2D) materials as a promising platform for the realization of transparent, flexible, ultra-thin memristive synapses. However, unsupervised learning in a spiking neural network (SNN) facilitated by linearity and symmetry in synaptic weight update has not been explored thoroughly using the 2D materials platform. Here, we demonstrate that graphene/MoS2/SiOx/Ni synapses exhibit ideal linearity and symmetry when subjected to identical input pulses, which is essential for their role in online training of neural networks. The linearity in weight update holds for a range of pulse width, amplitude and number of applied pulses. Our work illustrates that the mechanism of switching in MoS2-based synapses is through conductive filaments governed by Poole-Frenkel emission. We demonstrate that the graphene/MoS2/SiOx/Ni synapses, when integrated with a MoS2-based leaky integrate-and-fire neuron, can control the spiking of the neuron efficiently. This work establishes 2D MoS2as a viable platform for all-memristive SNNs.
-
Driven by the expanse of Internet of Things (IoT) and Cyber-Physical Systems (CPS), there is an increasing demand to process streams of temporal data on embedded devices with limited energy and power resources. Among all potential solutions, neuromorphic computing with spiking neural networks (SNN) that mimic the behavior of brain, have recently been placed at the forefront. Encoding information into sparse and distributed spike events enables low-power implementations, and the complex spatial temporal dynamics of synapses and neurons enable SNNs to detect temporal pattern. However, most existing hardware SNN implementations use simplified neuron and synapse models ignoring synapse dynamic, which is critical for temporal pattern detection and other applications that require temporal dynamics. To adopt a more realistic synapse model in neuromorphic platform its significant computation overhead must be addressed. In this work, we propose an FPGA-based SNN with biologically realistic neuron and synapse for temporal information processing. An encoding scheme to convert continuous real-valued information into sparse spike events is presented. The event-driven implementation of synapse dynamic model and its hardware design that is optimized to exploit the sparsity are also presented. Finally, we train the SNN on various temporal pattern-learning tasks and evaluate its performance and efficiency as compared to rate-based models and artificial neural networks on different embedded platforms. Experiments show that our work can achieve 10X speed up and 196X gains in energy efficiency compared with GPU.more » « less
