The TENNLab Exploratory Neuromorphic Computing Framework

Plank, James S.; Schuman, Catherine D.; Bruer, Grant; Dean, Mark E.; Rose, Garrett S.

doi:10.1109/locs.2018.2885976

Cited by 51 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future work, we intend to fully integrate the Hierarchical-PABO approach into the TENNLab neuromorphic framework by Plank et al ( 2018 ), so that it can seamlessly determine hyperparameters for the neuromorphic framework user. Within that framework, we also intend to apply this hyperparameter framework to other neuromorphic implementations that are supported and other applications, including a variety of control applications (like those described by Plank et al, 2019 ) and other classification tasks.…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…In SNN domain, we utilize a modified version of the TENNLab neuromorphic software framework (Plank et al, 2017(Plank et al, , 2018. This platform enables studying different applications and evaluating them on several neuromorphic processor implementations.…”

Section: Methodsmentioning

confidence: 99%

“…For artificial neural networks, we validated our approach using AlexNet (Krizhevsky et al, 2012) and VGG19 (Simonyan and Zisserman, 2014) on a Programmable Ultra-Efficient Memristor-based Accelerator (PUMA, Ankit et al, 2019). For spiking neuromorphic systems, we considered several control and classification tasks such as the canonical pole balancing (Gomez et al, 2006), autonomous robotic navigation (Mitchell et al, 2017), satellite radio signal classification (Reynolds et al, 2018), and Iris dataset classification (Dua and Graff, 2017) on both digital and mixed-signal memristor-based accelerators as the underlying hardware (Chakma et al, 2017;Mitchell et al, 2018;Plank et al, 2018). Hierarchical-PABO predicts the Pareto frontier for a three-objective (network performance, the accelerator's energy efficiency, and area) optimization with relatively few evaluations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2020

Self Cite

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

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…We focus on two approaches for training neuromorphic networks for control: evolutionary approaches and imitation learning. Genetic or evolutionary approaches have been commonly used to produce neuromorphic solutions to a variety of control tasks, including robotic control [2,28], drone control [21], video games [37], and engine control [45]. Imitation learning has also been popularly used for control of neuromorphic systems, especially for self-driving robots [17,22].…”

Section: Background and Related Workmentioning

confidence: 99%

Evolutionary vs imitation learning for neuromorphic control at the edge*

Schuman

Patton

Kulkarni

et al. 2022

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.

show abstract

“…In this work we leverage an evolutionary optimization framework called EONS [13], [14] to train spiking neural networks. This evolutionary approach has been shown to lead to well-performing SNNs, as demonstrated on several machine learning and control tasks [6], [15], [16].…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks

Dimovska

Johnston

Schuman

et al. 2019

2019 IEEE 10th Annual Ubiquitous Computing, Electronics &Amp; Mobile Communication Conference (UEMCON)

Self Cite

View full text Add to dashboard Cite

Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the developed hardware can greatly depend on the size of the network that is being evaluated on the chip. Furthermore, the accuracy of a trained SNN that is evaluated on chip can change due to voltage and current variations in the hardware that perturb the learned weights of the network. While efforts are made on the hardware side to minimize those perturbations, a software based strategy to make the deployed networks more resilient can help further alleviate that issue. In this work, we study Spiking Neural Networks in two neuromorphic architecture implementations with the goal of decreasing their size, while at the same time increasing their resiliency to hardware faults. We leverage an evolutionary algorithm to train the SNNs and propose a multiobjective fitness function to optimize the size and resiliency of the SNN. We demonstrate that this strategy leads to well-performing, small-sized networks that are more resilient to hardware faults.

show abstract

The TENNLab Exploratory Neuromorphic Computing Framework

Cited by 51 publications

References 16 publications

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

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

Evolutionary vs imitation learning for neuromorphic control at the edge*

Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks

Contact Info

Product

Resources

About