Neuromorphic Hardware Learns to Learn

Bohnstingl, Thomas; Scherr, Franz; Pehle, Christian; Meier, K.; Maass, Wolfgang

doi:10.3389/fnins.2019.00483

Cited by 40 publications

(38 citation statements)

References 29 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few-shot learning using biological models and synaptic plasticities is an appealing open problem, but there are few relevant studies, mainly because of a lack of algorithms and data. Existing algorithms attempt to solve it by exploring the learning-to-learn (L2L; Bellec et al, 2018;Bohnstingl et al, 2019) or transfer learning (Stewart et al, 2020) approach. However, these methods have poor performance and are subject to many restrictions, such as specific structures or simple tasks.…”

Section: Discussionmentioning

confidence: 99%

“…A special recurrent SNN with adapting neurons (LSNN) is suitable for L2L, which can approach the knowledge transfer performance of LSTM networks, but the universality of this algorithm to other SNN structures is not addressed (Bellec, Salaj, Subramoney, Legenstein, & Maass, 2018). With the aid of powerful gradient-free optimization tools, L2L also enhances the reward-based learning capability of SNNs in neuromorphic hardware (Bohnstingl, Scherr, Pehle, Meier, & Maass, 2019). Even so, these methods are limited to relatively simple learning tasks, such as learning the nonlinear functions from a teacher network or the reinforcement learning of multiarmed bandits.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

et al. 2021

View full text Add to dashboard Cite

Learning new concepts rapidly from a few examples is an open issue in spike-based machine learning. This few-shot learning imposes substantial challenges to the current learning methodologies of spiking neuron networks (SNNs) due to the lack of task-related priori knowledge. The recent learning-to-learn (L2L) approach allows SNNs to acquire priori knowledge through example-level learning and task-level optimization. However, an existing L2L-based framework does not target the neural dynamics (i.e., neuronal and synaptic parameter changes) on different timescales. This diversity of temporal dynamics is an important attribute in spike-based learning, which facilitates the networks to rapidly acquire knowledge from very few examples and gradually integrate this knowledge. In this work, we consider the neural dynamics on various timescales and provide a multi-timescale optimization (MTSO) framework for SNNs. This framework introduces an adaptive-gated LSTM to accommodate two different timescales of neural dynamics: short-term learning and long-term evolution. Short-term learning is a fast knowledge acquisition process achieved by a novel surrogate gradient online learning (SGOL) algorithm, where the LSTM guides gradient updating of SNN on a short timescale through an adaptive learning rate and weight decay gating. The long-term evolution aims to slowly integrate acquired knowledge and form, which can be achieved by optimizing the LSTM guidance process to tune SNN parameters on a long timescale. Experimental results demonstrate that the collaborative optimization of multi-timescale neural dynamics can make SNNs achieve promising performance for the few-shot learning tasks.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This learning-to-learn framework was recently applied to SNNs to obtain properties of LSTM networks and use them to solve complex sequence learning tasks (Bellec et al, 2018 ). In Bohnstingl et al ( 2019 ), the learning-to-learn framework was also applied to a neuromorphic hardware platform.…”

Section: Algorithms For Biologically Plausible Continual Learningmentioning

confidence: 99%

Adaptive Extreme Edge Computing for Wearable Devices

et al. 2021

View full text Add to dashboard Cite

Wearable devices are a fast-growing technology with impact on personal healthcare for both society and economy. Due to the widespread of sensors in pervasive and distributed networks, power consumption, processing speed, and system adaptation are vital in future smart wearable devices. The visioning and forecasting of how to bring computation to the edge in smart sensors have already begun, with an aspiration to provide adaptive extreme edge computing. Here, we provide a holistic view of hardware and theoretical solutions toward smart wearable devices that can provide guidance to research in this pervasive computing era. We propose various solutions for biologically plausible models for continual learning in neuromorphic computing technologies for wearable sensors. To envision this concept, we provide a systematic outline in which prospective low power and low latency scenarios of wearable sensors in neuromorphic platforms are expected. We successively describe vital potential landscapes of neuromorphic processors exploiting complementary metal-oxide semiconductors (CMOS) and emerging memory technologies (e.g., memristive devices). Furthermore, we evaluate the requirements for edge computing within wearable devices in terms of footprint, power consumption, latency, and data size. We additionally investigate the challenges beyond neuromorphic computing hardware, algorithms and devices that could impede enhancement of adaptive edge computing in smart wearable devices.

show abstract

“…For artificial neural networks (ANNs), these techniques span from simplifying models, such as pruning and quantization (Han et al, 2015;Wen et al, 2016;Yang et al, 2018;Zoph et al, 2018), to designing energy efficient architectures (Jin et al, 2014;Panda et al, 2016;Parsa et al, 2017;Wang et al, 2017), and neural architecture search (Zoph et al, 2018). In spiking neuromorphic domain, these include different training algorithms such as Schuman et al (2016), Bohnstingl et al (2019) based on evolutionary optimization, Esser et al (2015Esser et al ( , 2016 on modified backpropagation techniques, Severa et al (2019) as binary communication, and Rathi et al (2020) as a hybrid approach and then deploying these on neuromorphic hardware such as Schmitt et al (2017) and Koo et al (2020). In this section, we briefly introduce each of these methods and continue with the added complexity of co-designing hardware and software for artificial neural networks and spiking neuromorphic systems.…”

Section: Background and Related Workmentioning

confidence: 99%

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

et al. 2020

View full text Add to dashboard Cite

In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable. Embedding intelligence can be achieved using neural networks on neuromorphic hardware. Designing such networks would require determining several inherent hyperparameters. A key challenge is to find the optimum set of hyperparameters that might belong to the input/output encoding modules, the neural network itself, the application, or the underlying hardware. In this work, we present a hierarchical pseudo agent-based multi-objective Bayesian hyperparameter optimization framework (both software and hardware) that not only maximizes the performance of the network, but also minimizes the energy and area requirements of the corresponding neuromorphic hardware. We validate performance of our approach (in terms of accuracy and computation speed) on several control and classification applications on digital and mixed-signal (memristor-based) neural accelerators. We show that the optimum set of hyperparameters might drastically improve the performance of one application (i.e., 52–71% for Pole-Balance), while having minimum effect on another (i.e., 50–53% for RoboNav). In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.

show abstract

Neuromorphic Hardware Learns to Learn

Cited by 40 publications

References 29 publications

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization

Adaptive Extreme Edge Computing for Wearable Devices

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

Contact Info

Product

Resources

About