AHEAD: Automatic Holistic Energy-Aware Design Methodology for MLP Neural Network Hardware Generation in Proactive BMI Edge Devices

Nan-Sheng Huang,Jørgen Christian Larsen,Yi-Chung Chen,Poramate Manoonpong

doi:10.3390/en13092180

Nan-Sheng Huang, Jørgen Christian Larsen + Show 2 more

Open Access

https://doi.org/10.3390/en13092180

Copy DOI

Journal: Energies	Publication Date: May 1, 2020
Citations: 2	License type: CC BY 4.0

Affiliation: Maersk (Denmark), University of Southern Denmark

Abstract

The prediction of a high-level cognitive function based on a proactive brain–machine interface (BMI) control edge device is an emerging technology for improving the quality of life for disabled people. However, maintaining the stability of multiunit neural recordings is made difficult by the nonstationary nature of neurons and can affect the overall performance of proactive BMI control. Thus, it requires regular recalibration to retrain a neural network decoder for proactive control. However, retraining may lead to changes in the network parameters, such as the network topology. In terms of the hardware implementation of the neural decoder for real-time and low-power processing, it takes time to modify or redesign the hardware accelerator. Consequently, handling the engineering change of the low-power hardware design requires substantial human resources and time. To address this design challenge, this work proposes AHEAD: an automatic holistic energy-aware design methodology for multilayer perceptron (MLP) neural network hardware generation in proactive BMI edge devices. By taking a holistic analysis of the proactive BMI design flow, the approach makes judicious use of the intelligent bit-width identification (BWID) and configurable hardware generation, which autonomously integrate to generate the low-power hardware decoder. The proposed AHEAD methodology begins with the trained MLP parameters and golden datasets and produces an efficient hardware design in terms of performance, power, and area (PPA) with the least loss of accuracy. The results show that the proposed methodology is up to a 4X faster in performance, 3X lower in terms of power consumption, and achieves a 5X reduction in area resources, with exact accuracy, compared to floating-point and half-floating-point design on a field-programmable gate array (FPGA), which makes it a promising design methodology for proactive BMI edge devices.

Highlights

A brain–machine interface (BMI) is a direct and unconventional communication link between the brain and a physical device [1,2]
The effectiveness of the automatic holistic energy-aware design (AHEAD) methodology is validated with two cases from proactive BMI recalibration experiments that demonstrate the full range of the methodology’s capabilities
multilayer perceptron (MLP) hardware accelerators with FP32 and FP16, which are based on the same MLP microarchitecture, were implemented as benchmarks, respectively

Summary

Introduction

A brain–machine interface (BMI) is a direct and unconventional communication link between the brain and a physical device [1,2] It enables the study of neuronal activity, representing cognitive processes of planning and mental simulation of action sequences. Plan4Act [10] is a European project to proactively predict the future planned actions of an agent by extracting this planning knowledge from the agent’s neuronal activities The basis for this is recent experimental results that show that complex planning and sequencing information is represented by neural activity in the (monkey) brain [31,32]. Action sequences AB may lead to the different following actions C1 or C2 , since the common path is AB

Objectives

Results

Conclusion