Spiking neural network (SNN) control of a flapping insect-scale robot

Clawson, Taylor S.; Ferrari, Silvia; Fuller, Sharon; Wood, Robert J.

doi:10.1109/cdc.2016.7798778

Cited by 46 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Problems that require us to estimate continuous numbers bring out the architectural limitations that might arise if the goal is to predict large range of numbers. On the other hand, benchmarks from domains such as Micro-Aerial Vehicles (Ma et al, 2013) and video surveillance would be very interesting for the SNN community because these small drones already have SNN controllers in them (Clawson et al, 2016). Having video surveillance dataset from MAVs, will help us realize potential of SNNs to be deployed in energy-constrained environments.…”

Section: Discussionmentioning

confidence: 99%

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

et al. 2019

View full text Add to dashboard Cite

In this work, we perform analysis of detection and counting of cars using a low-power IBM TrueNorth Neurosynaptic System. For our evaluation we looked at a publicly-available dataset that has overhead imagery of cars with context present in the image. The trained neural network for image analysis was deployed on the NS16e system using IBM's EEDN training framework. Through multiple experiments we identify the architectural bottlenecks present in TrueNorth system that does not let us deploy large neural network structures. Following these experiments we propose changes to CNN model to circumvent these architectural bottlenecks. The results of these evaluations have been compared with caffe-based implementations of standard neural networks that were deployed on a Titan-X GPU. Results showed that TrueNorth can detect cars from the dataset with 97.60% accuracy and can be used to accurately count the number of cars in the image with 69.04% accuracy. The car detection accuracy and car count (–/+ 2 error margin) accuracy are comparable to high-precision neural networks like AlexNet, GoogLeNet, and ResCeption, but show a manifold improvement in power consumption.

show abstract

Section: Discussionmentioning

confidence: 99%

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

et al. 2019

View full text Add to dashboard Cite

show abstract

“…This is usually achieved by strengthening or weakening the connections that lead to changes in the objective function based on their eligibility traces. Clawson et al ( 2016 ) used this basic architecture to train an SNN to follow a trajectory. The network consisted of lateral state variables as inputs, a hidden layer and an output layer population decoding the lateral control output.…”

Section: Learning and Robotics Applicationsmentioning

confidence: 99%

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

et al. 2018

View full text Add to dashboard Cite

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.

show abstract

“…This makes parallel encoding feasible, because all the samples are known a priori and rearrangement is possible. Yet, as References [5,10] argue, there exist ultra-low power applications where the sensory data is already a bitstream. Under these constraints, using binary data is an unnecessary and costly bottleneck, but without the ability to generate all T samples prior to compute, the parallel encoding scheme would not be possible.…”

Section: Differences Between Population Coding and Parallel Encodingmentioning

confidence: 99%

B it SAD v2

Daruwalla

Zhuo

Shukla

et al. 2019

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

Computer vision and machine learning algorithms operating under a strict power budget require an alternate computing paradigm. While bitstream computing (BC) satisfies these constraints, creating BC systems is difficult. To address the design challenges, we propose compiler extensions to BitSAD, a DSL for BC. Our work enables bit-level software emulation and automated generation of hierarchical hardware, discusses potential optimizations, and proposes compiler phases to implement those optimizations in a hardware-aware manner. Finally, we introduce population coding, a parallelization scheme for stochastic computing that decreases latency without sacrificing accuracy, and provide theoretical and experimental guarantees on its effectiveness.

show abstract

Spiking neural network (SNN) control of a flapping insect-scale robot

Cited by 46 publications

References 24 publications

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

B it SAD v2

Contact Info

Product

Resources

About