ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Multiplierless In-filter Computing for tinyML Platforms

Nair, AR and Nath, PK and Chakrabartty, S and Thakur, CS (2024) Multiplierless In-filter Computing for tinyML Platforms. In: 37th International Conference on VLSI Design, VLSID 2024, 6 January 2024through 10 January 2024, Kolkata, West Bengal, pp. 192-197.

[img]
Preview
PDF
pro_iee_int_con_vls_des_2024.pdf - Published Version

Download (499kB) | Preview
Official URL: https://doi.org/10.1109/VLSID60093.2024.00038

Abstract

Wildlife conservation using continuous monitoring of environmental factors and biomedical classification, which generate a vast amount of sensor data, is a challenge due to limited bandwidth in the case of remote monitoring. It becomes critical to have classification where data is generated. We present a novel multiplierless framework for in-filter acoustic classification using Margin Propagation (MP) approximation used in low-power edge devices deployable in remote areas with limited connectivity. The entire design of this classification framework is based on template-based kernel machine, which uses basic primitives like addition/subtraction, shift, and comparator operations, for hardware implementation. Unlike full precision training methods for traditional classification, we use MP-based approximation for training, including backpropagation mitigating approximation errors. The proposed framework is general enough for acoustic classification. However, we demonstrate the hardware friendliness of this framework by implementing a parallel Finite Impulse Response (FIR) filter bank in a kernel machine classifier optimized for a Field Programmable Gate Array (FPGA). The FIR filter acts as the feature extractor and non-linear kernel for the kernel machine implemented using MP approximation. The FPGA implementation on Spartan 7 shows that the MP-approximated in-filter kernel machine is more efficient than traditional classification frameworks with just less than 1K slices. © 2024 IEEE.

Item Type: Conference Paper
Publication: Proceedings of the IEEE International Conference on VLSI Design
Publisher: IEEE Computer Society
Additional Information: The copyright for this article belongs to authors.
Keywords: Conservation; Edge computing; Field programmable gate arrays (FPGA); Impulse response; Internet of things, Acoustic classification; Classification framework; Edge computing; Field programmable gate array; Field programmables; IoT; Kernel machine; Multiplierless; Programmable gate array; Wildlife conservation, FIR filters
Department/Centre: Division of Electrical Sciences > Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology)
Date Deposited: 28 Aug 2024 11:52
Last Modified: 28 Aug 2024 11:52
URI: http://eprints.iisc.ac.in/id/eprint/84866

Actions (login required)

View Item View Item