Training Neural Networks for Execution on Approximate Hardware

2023/04/08 by Tianmu Li, Li, Tianmu, Shurui Li +3
Engineering · #Advanced Memory and Neural Computing #Advancements in Semiconductor Devices and Circuit Design #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2304.04125

openalex publication_date 2023/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Approximate computing methods have shown great potential for deep learning. Due to the reduced hardware costs, these methods are especially suitable for inference tasks on battery-operated devices that are constrained by their power budget. However, approximate computing hasn't reached its full potential due to the lack of work on training methods. In this work, we discuss training methods for approximate hardware. We demonstrate how training needs to be specialized for approximate hardware, and propose methods to speed up the training process by up to 18X.

Related

• Invocation-driven Neural Approximate Computing with a Multiclass-Classifier and Multiple Approximators
• Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
• Hardware-Aware Machine Learning: Modeling and Optimization
• Learning Machines Implemented on Non-Deterministic Hardware
• AX-DBN: An Approximate Computing Framework for the Design of Low-Power Discriminative Deep Belief Networks