paper-with-me

Papers

Measuring what Really Matters: Optimizing Neural Networks for TinyML

2021-04-21 · Lennart Heim, Andreas Biri, Zhongnan Qu, Lothar Thiele

With the surge of inexpensive computational and memory resources, neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity. Introducing NNs to resource-constrained devices enables cost-efficient deployments, widespread availability, and the preservation of sensitive data. This work addresses the challenges of bringing Machine Learning to MCUs, where we focus on the ubiquitous ARM Cortex-M architecture. The detailed effects and trade-offs that optimization methods, software frameworks, and MCU hardware architecture have on key performance metrics such as inference latency and energy consumption have not been previously studied in depth for state-of-the-art frameworks such as TensorFlow Lite Micro. We find that empirical investigations which measure the perceptible metrics - performance as experienced by the user - are indispensable, as the impact of specialized instructions and layer types can be subtle. To this end, we propose an implementation-aware design as a cost-effective method for verification and benchmarking. Employing our developed toolchain, we demonstrate how existing NN deployments on resource-constrained devices can be improved by systematically optimizing NNs to their targeted application scenario.

📄 PDF Abstract BibTeX arXiv:2104.10645

Code (2)

lheim/TFLM-Evaluation
lheim/TFLM-Toolchain tf

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

ANN Search: Recall What Matters

2026-06-03 · Dimitris Dimitropoulos, Nikos Mamoulis arxiv

Approximate nearest neighbor (ANN) search has become a core primitive in information retrieval and modern machine learning tasks, from classification to retrieval-augmented generation. The community evaluates and tunes A…

Information RetrievalSemantic Similarity

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

2025-11-03 · Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner 외 arxiv

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as 'safety'…

Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?

2022-06-16 · Adam W. Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus 외

Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors. Recent research …

Autonomous VehiclesBird's-Eye View Semantic SegmentationData Augmentation

Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers

2024-09-17 · Riya Samanta, Bidyut Saha, Soumya K. Ghosh, Ram Babu Roy

Tiny Machine Learning (TinyML) enables efficient, lowcost, and privacy preserving machine learning inference directly on microcontroller units (MCUs) connected to sensors. Optimizing models for these constrained environm…

Privacy PreservingTime SeriesTime Series Classification

Corporate core values and social responsibility: What really matters to whom

2021-06-03 · M. A. Barchiesi, A. Fronzetti Colladon

This study uses an innovative measure, the Semantic Brand Score, to assess the interest of stakeholders in different company core values. Among others, we focus on corporate social responsibility (CSR) core value stateme…