English
Related papers

Related papers: TinyD\'ej\`aVu: Smaller RAM and Faster Inference w…

200 papers

Deep Neural Network (DNN) based inference at the edge is challenging as these compute and data-intensive algorithms need to be implemented at low cost and low power while meeting the latency constraints of the target applications. Sparsity,…

Neural and Evolutionary Computing · Computer Science 2023-06-13 Adithya Krishna , Srikanth Rohit Nudurupati , Chandana D G , Pritesh Dwivedi , André van Schaik , Mahesh Mehendale , Chetan Singh Thakur

Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…

Computer Vision and Pattern Recognition · Computer Science 2021-11-08 Abhinav Goel , Caleb Tung , Xiao Hu , George K. Thiruvathukal , James C. Davis , Yung-Hsiang Lu

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…

Machine Learning · Computer Science 2021-08-04 Thomas Pfeil

As spiking-based deep learning inference applications are increasing in embedded systems, these systems tend to integrate neuromorphic accelerators such as $\mu$Brain to improve energy efficiency. We propose a $\mu$Brain-based scalable…

Neural and Evolutionary Computing · Computer Science 2021-11-24 M. Lakshmi Varshika , Adarsha Balaji , Federico Corradi , Anup Das , Jan Stuijt , Francky Catthoor

Compute-in-memory (CIM) accelerators using non-volatile memory (NVM) devices offer promising solutions for energy-efficient and low-latency Deep Neural Network (DNN) inference execution. However, practical deployment is often hindered by…

Hardware Architecture · Computer Science 2024-08-23 Yifan Qin , Zheyu Yan , Zixuan Pan , Wujie Wen , Xiaobo Sharon Hu , Yiyu Shi

Specialized compute blocks have been developed for efficient DNN execution. However, due to the vast amount of data and parameter movements, the interconnects and on-chip memories form another bottleneck, impairing power and performance.…

Machine Learning · Computer Science 2023-11-10 Lennart Bamberg , Ardalan Najafi , Alberto Garcia-Ortiz

AI spans from large language models to tiny models running on microcontrollers (MCUs). Extremely memory-efficient model architectures are decisive to fit within an MCU's tiny memory budget e.g., 128kB of RAM. However, inference latency must…

Machine Learning · Computer Science 2025-10-20 Zhaolan Huang , Emmanuel Baccelli

We present the MEMA framework for the easy and quick derivation of efficient inference runtimes that minimize external memory accesses for matrix multiplication on TinyML systems. The framework accounts for hardware resource constraints and…

Machine Learning · Computer Science 2023-04-13 Andrew Sabot , Vikas Natesh , H. T. Kung , Wei-Te Ting

This paper presents a novel event-based eye-tracking system deployed on a resource-constrained microcontroller, addressing the challenges of real-time, low-latency, and low-power performance in embedded systems. The system leverages a…

Hardware Architecture · Computer Science 2025-08-20 Marco Giordano , Pietro Bonazzi , Luca Benini , Michele Magno

On-device training is essential for user personalisation and privacy. With the pervasiveness of IoT devices and microcontroller units (MCUs), this task becomes more challenging due to the constrained memory and compute resources, and the…

Machine Learning · Computer Science 2024-06-12 Young D. Kwon , Rui Li , Stylianos I. Venieris , Jagmohan Chauhan , Nicholas D. Lane , Cecilia Mascolo

Reducing the memory footprint of neural networks is a crucial prerequisite for deploying them in small and low-cost embedded devices. Network parameters can often be reduced significantly through pruning. We discuss how to best represent…

Data Structures and Algorithms · Computer Science 2021-11-25 Elias Trommer , Bernd Waschneck , Akash Kumar

Embedded and IoT devices, largely powered by microcontroller units (MCUs), could be made more intelligent by leveraging on-device deep learning. One of the main challenges of neural network inference on an MCU is the extremely limited…

Machine Learning · Computer Science 2023-01-25 Edgar Liberis , Nicholas D. Lane

Nowadays, Neural Networks represent a major expectation for the realization of powerful Deep Learning algorithms, which can determine several physical systems' behaviors and operations. Computational resources required for model, training,…

Machine Learning · Computer Science 2021-03-02 Giulia Crocioni , Giambattista Gruosso , Danilo Pau , Davide Denaro , Luigi Zambrano , Giuseppe di Giore

The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…

Machine Learning · Computer Science 2021-11-05 Jun-Liang Lin , Sheng-De Wang

Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…

Machine Learning · Computer Science 2024-11-15 Jinjie Liu , Hang Qiu

In this paper, we propose StruM, a novel structured mixed-precision-based deep learning inference method, co-designed with its associated hardware accelerator (DPU), to address the escalating computational and memory demands of deep…

Hardware Architecture · Computer Science 2025-05-20 Michael Wu , Arnab Raha , Deepak A. Mathaikutty , Martin Langhammer , Engin Tunali , Daksha Sharma

Graphics processing units (GPUs) excel at parallel processing, but remain largely unexplored in ultra-low-power edge devices (TinyAI) due to their power and area limitations, as well as the lack of suitable programming frameworks. To…

Hardware Architecture · Computer Science 2026-03-17 Simone Machetti , Pasquale Davide Schiavone , Lara Orlandic , Darong Huang , Deniz Kasap , Giovanni Ansaloni , David Atienza

Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed…

Machine Learning · Computer Science 2024-01-31 Kun Wang , Jiani Cao , Zimu Zhou , Zhenjiang Li

Low-power microcontroller (MCU) hardware is currently evolving from single-core architectures to predominantly multi-core architectures. In parallel, new embedded software building blocks are more and more written in Rust, while C/C++…

Machine Learning · Computer Science 2026-05-28 Zhaolan Huang , Kaspar Schleiser , Gyungmin Myung , Emmanuel Baccelli

Current AI training infrastructure is dominated by single instruction multiple data (SIMD) and systolic array architectures, such as Graphics Processing Units (GPUs) and Tensor Processing Units (TPUs), that excel at accelerating parallel…

Neural and Evolutionary Computing · Computer Science 2023-11-09 Jan Finkbeiner , Thomas Gmeinder , Mark Pupilli , Alexander Titterton , Emre Neftci