Big Data Management in Neural Implants: The Neuromorphic Approach

Basu, Arindam; Chen, Yi; Yao, Enyi

doi:10.1007/978-3-319-54840-1_14

Cited by 9 publications

(9 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This problem only worsens further with increasing channel count [10], [11] hindering scalability due to overheating [12] as well as hitting bandwidth constraints [13]. An alternative proposed architecture to address this issue [14] is to do signal processing up to decoding in the implant itself as indicated in Fig. 1(b).…”

Section: Introductionmentioning

confidence: 99%

Towards Intelligent Intracortical BMI (i$^2$BMI): Low-Power Neuromorphic Decoders That Outperform Kalman Filters

Shaikh

Sibindi

et al. 2019

IEEE Trans. Biomed. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

Fully implantable wireless intra-cortical Brain Machine Interfaces (iBMI) is one of the most promising next frontiers in the nascent field of neurotechnology. However, scaling the number of channels in such systems by another 10X is difficult due to power and bandwidth requirements of the wireless transmitter. One promising solution for that is to include more processing, up to the decoder, in the implant so that transmission data rate is reduced drastically. Earlier work on neuromorphic decoders only showed classification of discrete states. We present results for continuous state decoding using a low power neuromorphic decoder chip termed Spike-input Extreme Learning Machine (SELMA). We compared SELMA against state of the art Steady State Kalman Filter (SSKF) across two different datasets involving a total of 4 non-human primates (NHPs). Results show at least a 10% or more increase in the fraction of variance accounted for by SELMA over SSKF across the datasets. Furthermore, estimated energy consumption comparison shows SELMA consuming ≈ 9 nJ/update against SSKF's ≈ 7.4 nJ/update for an iBMI with a 10 degree of freedom control. Thus, SELMA yields better performance against SSKF with a marginal increase in energy consumption paving the way for reducing transmission data rates in future scaled BMI systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Intelligent Intracortical BMI (i$^2$BMI): Low-Power Neuromorphic Decoders That Outperform Kalman Filters

Shaikh

Sibindi

et al. 2019

IEEE Trans. Biomed. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…D EEP Neural Networks (DNN) are gaining popularity recently in many applications such as face recognition [1], speech recognition [2], natural language processing [3] etc due to improved performance compared to other machine learning algorithms. Deploying these networks at the edge in the Internet of Things (IoT) is important for scalability and fast response by reducing data transmission to the cloud [4], [5]. However, due to battery life and processing constraints, it is imperative to have low power, low area implementations of the DNN.…”

Section: Introductionmentioning

confidence: 99%

A 0.11–0.38 pJ/cycle Differential Ring Oscillator in 65 nm CMOS for Robust Neurocomputing

Zhang

Acharya

Basu

2021

IEEE Trans. Circuits Syst. I

Self Cite

View full text Add to dashboard Cite

This paper presents a low-area and low-power consumption CMOS differential current controlled oscillator (CCO) for neuromorphic applications. The oscillation frequency is improved over the conventional one by reducing the number of MOS transistors thus lowering the load capacitor in each stage. The analysis shows that for the same power consumption, the oscillation frequency can be increased about 11% compared with the conventional one without degrading the phase noise. Alternatively, the power consumption can be reduced 15% at the same frequency. The prototype structures are fabricated in a standard 65 nm CMOS technology and measurements demonstrate that the proposed CCO operates from 0.7 − 1.2 V supply with maximum frequencies of 80 MHz and energy/cycle ranging from 0.11 − 0.38 pJ over the tuning range. Further, system level simulations show that the nonlinearity in currentfrequency conversion by the CCO does not affect its use as a neuron in a Deep Neural Network if accounted for during training.

show abstract

“…Firstly, most iBMI systems use wired connection to bulky computers reducing patient mobility and increasing risk of infection [8]. Wireless iBMIs suffer from scalability issues due to exploding data rates [9]. A potential solution is including an intention decoder in the implant [10]; however, the need for frequent retraining makes it impractical.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Reinforcement Algorithms for autonomous, scalable intra-cortical Brain Machine Interfaces

Shaikh

Sibindi

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Intra-cortical Brain Machine Interfaces (iBMIs) with wireless capability could scale the number of recording channels by integrating an intention decoder to reduce data rates. However, the need for frequent retraining due to neural signal non-stationarity is a big impediment. This paper presents an alternate paradigm of online reinforcement learning (RL) with a binary evaluative feedback in iBMIs to tackle this issue. This paradigm eliminates time-consuming calibration procedures. Instead, it relies on updating the model on a sequential sample-by-sample basis based on an instantaneous evaluative binary feedback signal. However, batch updates of weight in popular deep networks is very resource consuming and incompatible with constraints of an implant. In this work, using offline open-loop analysis on pre-recorded data, we show application of a simple RL algorithm - Banditron -in discrete-state iBMIs and compare it against previously reported state of the art RL algorithms – Hebbian RL, Attention gated RL, deep Q-learning. Owing to its simplistic single-layer architecture, Banditron is found to yield at least two orders of magnitude of reduction in power dissipation compared to state of the art RL algorithms. At the same time, post-hoc analysis performed on four pre-recorded experimental datasets procured from the motor cortex of two non-human primates performing joystick-based movement-related tasks indicate Banditron performing significantly better than state of the art RL algorithms by at least 5%, 10%, 7% and 7% in experiments 1, 2, 3 and 4 respectively. Furthermore, we propose a non-linear variant of Banditron, Banditron-RP, which gives an average improvement of 6%, 2% in decoding accuracy in experiments 2,4 respectively with only a moderate increase in power consumption.

show abstract

Big Data Management in Neural Implants: The Neuromorphic Approach

Cited by 9 publications

References 70 publications

Towards Intelligent Intracortical BMI (i$^2$BMI): Low-Power Neuromorphic Decoders That Outperform Kalman Filters

Towards Intelligent Intracortical BMI (i$^2$BMI): Low-Power Neuromorphic Decoders That Outperform Kalman Filters

A 0.11–0.38 pJ/cycle Differential Ring Oscillator in 65 nm CMOS for Robust Neurocomputing

Lightweight Reinforcement Algorithms for autonomous, scalable intra-cortical Brain Machine Interfaces

Contact Info

Product

Resources

About