Neuromorphic Analog Implementation of Neural Engineering Framework-Inspired Spiking Neuron for High-Dimensional Representation

Hazan, Avi; Tsur, Elishai Ezra

doi:10.3389/fnins.2021.627221

Cited by 14 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is since spanning high-dimensional space (as required by robotic systems with high DoF) requires a large number of neurons. 13 Recently, learning-based IK was implemented with SNNs, demonstrating how carefully tuned neuromorphic encoding can be used to perform high-dimensional nonlinear computations. 11 Here we further extend the discussion.…”

Section: Discussionmentioning

confidence: 99%

“… 11 It serves as the foundation for Nengo, a Python-based "neural compiler," which translates high-level descriptions to low-level neural models. 12 NEF-inspired neuromorphic hardware designs 13 have been implemented in both analog and digital circuitry. A version of it has been compiled to work on the most prominent neuromorphic hardware architectures available, including Intel's neuromorphic Loihi circuit.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics

et al. 2022

Self Cite

View full text Add to dashboard Cite

Summary Inverse kinematics is fundamental for computational motion planning. It is used to derive an appropriate state in a robot's configuration space, given a target position in task space. In this work, we investigate the performance of fully connected and residual artificial neural networks as well as recurrent, learning-based, and deep spiking neural networks for conventional and geometrically constrained inverse kinematics. We show that while highly parameterized data-driven neural networks with tens to hundreds of thousands of parameters exhibit sub-ms inference time and sub-mm accuracy, learning-based spiking architectures can provide reasonably good results with merely a few thousand neurons. Moreover, we show that spiking neural networks can perform well in geometrically constrained task space, even when configured to an energy-conserved spiking rate, demonstrating their robustness. Neural networks were evaluated on NVIDIA's Xavier and Intel's neuromorphic Loihi chip.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…NEF was utilized to design a wide range of SNN-driven applications, ranging from robotic control ( Zaidel et al, 2021 ) and visual processing ( Yun and Wong, 2021 ) to perception ( Eliasmith and Stewart, 2012 ) and pattern recognition ( Wang et al, 2017 ). NEF was shown to be incredibly versatile, as a version of it was compiled to work on both analog and digital neuromorphic circuitry ( Voelker, 2015 ; Hazan and Tsur, 2021 ). Power comparison between neuromorphic NEF-driven implementation of adaptive control to conventional CPU and GPU-based implementation, demonstrated increased power efficiency while preserving similar latency performance ( DeWolf et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Adaptive control of a wheelchair mounted robotic arm with neuromorphically integrated velocity readings and online-learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Wheelchair-mounted robotic arms support people with upper extremity disabilities with various activities of daily living (ADL). However, the associated cost and the power consumption of responsive and adaptive assistive robotic arms contribute to the fact that such systems are in limited use. Neuromorphic spiking neural networks can be used for a real-time machine learning-driven control of robots, providing an energy efficient framework for adaptive control. In this work, we demonstrate a neuromorphic adaptive control of a wheelchair-mounted robotic arm deployed on Intel’s Loihi chip. Our algorithm design uses neuromorphically represented and integrated velocity readings to derive the arm’s current state. The proposed controller provides the robotic arm with adaptive signals, guiding its motion while accounting for kinematic changes in real-time. We pilot-tested the device with an able-bodied participant to evaluate its accuracy while performing ADL-related trajectories. We further demonstrated the capacity of the controller to compensate for unexpected inertia-generating payloads using online learning. Videotaped recordings of ADL tasks performed by the robot were viewed by caregivers; data summarizing their feedback on the user experience and the potential benefit of the system is reported.

show abstract

“…New communication elements permit highly interconnected circuits to receive and integrate spikes from a scalable number of silicon neurons (SiNs) [41,42]. It is easy to connect multiple inputs to neuron integrators with capacitive crossbar arrays because they only use dynamic power and a lot less static power than the more common resistive crossbar array [43].…”

Section: Implementing Neural Network Circuitsmentioning

confidence: 99%

Recurrent neural network implementation of digital integrated circuits to mitigate challenges in design verification

Yeong,

2023

View full text Add to dashboard Cite

Design verification is the dominant stage that consumes the most resources in the digital integrated circuit (IC) design process. Design verification is important because human designers imperfectly convert high-level specifications to low-level circuit implementations using standard cell logic, which is nonlinear and complex to predict and characterize. The widening process variations in shrinking process technologies while digital designs grow in scale and complexity to the extent of being impossible to fully or intuitively identify all temporal interactions of a specific design. Deep neural networks (DNN) are being progressively integrated into the sophisticated software tool chain and design process flow of digital IC as artificial intelligence can learn relationships and correlations in complex, high-dimensional, and multi-factorial problems. In this work, we propose to apply DNN to implement digital IC to minimize the complexity of digital design verification. We posit that DNN can learn to implement circuit functions directly from high-level specifications without requiring detailed specifications from the designer. Trained neural networks can be implemented on neuromorphic hardware to achieve greater power and compute efficiencies than the conventional standard cell implementation. We demonstrate that over 150 randomly generated finite state machines (FSM) can be learned effectively with Recurrent Neural Network (RNN) comprising Gated Recurrent Units (GRU) with different complexity as indicated by the number of states and inputs to the FSM. Our proposed methodology of learning RNN GRU implementations of FSM demonstrates a way forward to reduce the cost and effort of design verification, ultimately leading towards faster digital IC design cycles.

show abstract

Neuromorphic Analog Implementation of Neural Engineering Framework-Inspired Spiking Neuron for High-Dimensional Representation

Cited by 14 publications

References 38 publications

Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics

Data-driven artificial and spiking neural networks for inverse kinematics in neurorobotics

Adaptive control of a wheelchair mounted robotic arm with neuromorphically integrated velocity readings and online-learning

Recurrent neural network implementation of digital integrated circuits to mitigate challenges in design verification

Contact Info

Product

Resources

About