An Energy-Efficient Spiking Neural Network for Finger Velocity Decoding for Implantable Brain-Machine Interface

Liao, Jiawei; Widmer, Lars; Wang, Xiaying; Mauro, Alfio Di; Nason, Samuel R.; Chestek, Cynthia A.; Benini, Luca; Jang, Taekwang

doi:10.1109/aicas54282.2022.9869846

Cited by 12 publications

(32 citation statements)

References 24 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a disadvantage of this method is that the membrane potential always starts at zero, which can lead to a poor fit when the kinematic data starts far from zero. A similar output encoding method was used in [15], but our method was developed independently prior to the release of that work.…”

Section: Regression Learning Methodsmentioning

confidence: 99%

“…While these methods remain popular, recent research has shown that the accuracy of SNNs can be far improved using error backpropagation [14]. One recent work used a SNN with backpropagation to perform neural decoding with comparable accuracy to a state-of-the-art neural network [15]. However, backpropagation methods are less biologically plausible than STDP, and require significant memory overhead.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex

Taeckens

Dong

Shah

2022

Preprint

View full text Add to dashboard Cite

This work presents a spiking neural network for predicting kinematics from neural data towards accurate and energy-efficient brain machine interface. A brain machine interface is a technological system that interprets neural signals to allow motor impaired patients to control prosthetic devices. Spiking neural networks have the potential to improve brain machine interface technology due to their low power cost and close similarity to biological neural structures. The SNN in this study uses the leaky integrate-and-fire model to simulate the behavior of neurons, and learns using a local learning method that uses surrogate gradient to learn the parameters of the network. The network implements a novel continuous time output encoding scheme that allows for regression-based learning. The SNN is trained and tested offline on neural and kinematic data recorded from the premotor cortex of a primate and the hippocampus of a rat. The model is evaluated by finding the correlation between the predicted kinematic data and true kinematic data, and achieves peak Pearson Correlation Coefficients of 0.77 for the premotor cortex recordings and 0.80 for the hippocampus recordings. The accuracy of the model is benchmarked against a Kalman filter decoder and a LSTM network, as well as a spiking neural network trained with backpropagation to compare the effects of local learning.

show abstract

Section: Regression Learning Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex

Taeckens

Dong

Shah

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To enable 2D cursors control with a SNN, the SNN output must be modified to produce two continuous real-values functions corresponding to the x and y components of predicted arm velocity. SNN decoders can be adapted to produce these functions by adding a readout layer consisting of two leaky-integrate neurons that never emit spikes [20,22], where the output is given by the neuron's membrane potential. This method of computing the output has several desirable properties, such as the fact that the membrane potential is a continuous and differentiable function, so there will be no unnatural instantaneous changes in the predicted velocity.…”

Section: Readout Functionmentioning

confidence: 99%

“…Previous work has explored the use of SNNs for neural decoding [19][20][21][22]. In [19], authors demonstrated an SNN that could replicate the behavior of a Kalman filter using the neural engineering framework.…”

Section: Introductionmentioning

confidence: 99%

“…More recent work has shown that SNNs trained with surrogate gradient descent can also provide highly accurate results. In [20] authors demonstrated that SNNs can achieve superior performance to Kalman filters and artificial neural networks for decoding finger velocity, while [22] showed an SNN decoder with comparable accuracy to an LSTM for decoding arm velocity or body position. However, there are still several challenges that need to be addressed before SNNs can become viable decoding options for a robust and accurate BMI.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A spiking neural network with continuous local learning for robust online brain machine interface

Taeckens,

Shah

2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Spiking neural networks (SNNs) are powerful tools that are well suited for brain machine interfaces (BMI) due to their similarity to biological neural systems and computational efficiency. They have shown comparable accuracy to state-of-the-art methods, but current training methods require large amounts of memory, and they cannot be trained on a continuous input stream without pausing periodically to perform backpropagation. An ideal BMI should be capable training continuously without interruption to minimize disruption to the user and adapt to changing neural environments. Approach. We propose a continuous SNN weight update algorithm that can be trained to perform regression learning with no need for storing past spiking events in memory. As a result, the amount of memory needed for training is constant regardless of the input duration. We evaluate the accuracy of the network on recordings of neural data taken from the premotor cortex of a primate performing reaching tasks. Additionally, we evaluate the SNN in a simulated closed loop environment and observe its ability to adapt to sudden changes in the input neural structure. Main results. The continuous learning SNN achieves the same peak correlation (ρ = 0.7) as existing SNN training methods when trained offline on real neural data while reducing the total memory usage by 92%. Additionally, it matches state-of-the-art accuracy in a closed loop environment, demonstrates adaptability when subjected to multiple types of neural input disruptions, and is capable of being trained online without any prior offline training. Significance. This work presents a neural decoding algorithm that can be trained rapidly in a closed loop setting. The algorithm increases the speed of acclimating a new user to the system and also can adapt to sudden changes in neural behavior with minimal disruption to the user.

show abstract

On-FPGA Spiking Neural Networks for Multi-variable End-to-End Neural Decoding

Leone,

Martis,

Raffo

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

An Energy-Efficient Spiking Neural Network for Finger Velocity Decoding for Implantable Brain-Machine Interface

Cited by 12 publications

References 24 publications

A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex

A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex

A spiking neural network with continuous local learning for robust online brain machine interface

On-FPGA Spiking Neural Networks for Multi-variable End-to-End Neural Decoding

Contact Info

Product

Resources

About