English
Related papers

Related papers: On-Device Training Under 256KB Memory

200 papers

Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes…

Machine Learning · Computer Science 2018-05-25 Yi Yang , Andy Chen , Xiaoming Chen , Jiang Ji , Zhenyang Chen , Yan Dai

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sayed Pedram Haeri Boroujeni , Niloufar Mehrabi , Patrick Woods , Gabriel Hillesheim , Abolfazl Razi

Sub-\SI{50}{\gram} nano-drones are gaining momentum in both academia and industry. Their most compelling applications rely on onboard deep learning models for perception despite severe hardware constraints (\ie sub-\SI{100}{\milli\watt}…

Robotics · Computer Science 2024-03-08 Elia Cereda , Manuele Rusci , Alessandro Giusti , Daniele Palossi

Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy. The success of FL hinges on the efficiency of participating models and their…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Chu Myaet Thwal , Minh N. H. Nguyen , Ye Lin Tun , Seong Tae Kim , My T. Thai , Choong Seon Hong

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be…

Machine Learning · Computer Science 2017-12-19 Benoit Jacob , Skirmantas Kligys , Bo Chen , Menglong Zhu , Matthew Tang , Andrew Howard , Hartwig Adam , Dmitry Kalenichenko

Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved…

Machine Learning · Computer Science 2021-04-13 Haoyu Ren , Darko Anicic , Thomas Runkler

Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. This paradigm is…

Machine Learning · Computer Science 2026-01-22 Monirul Islam Pavel , Siyi Hu , Mahardhika Pratama , Ryszard Kowalczyk

We study the factors affecting training time in multi-device deep learning systems. Given a specification of a convolutional neural network, our goal is to minimize the time to train this model on a cluster of commodity CPUs and GPUs. We…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-10-20 Stefan Hadjis , Ce Zhang , Ioannis Mitliagkas , Dan Iter , Christopher Ré

Transformers provide promising accuracy and have become popular and used in various domains such as natural language processing and computer vision. However, due to their massive number of model parameters, memory and computation…

Machine Learning · Computer Science 2021-07-01 Hamid Tabani , Ajay Balasubramaniam , Shabbir Marzban , Elahe Arani , Bahram Zonooz

IoT devices particularly microcontrollers are challenged by their inherent limitations in processing capabilities, memory capacity, and energy conservation. Securing communication within IoT networks is further complicated by the…

Cryptography and Security · Computer Science 2026-05-14 Vasilis Ieropoulos , Eirini Anthi , Theodoros Spyridopoulos , Pete Burnap , Aftab Khan , Pietro Carnelli

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

This paper aims to address the major challenges of Federated Learning (FL) on edge devices: limited memory and expensive communication. We propose a novel method, called Partial Variable Training (PVT), that only trains a small subset of…

Machine Learning · Computer Science 2021-10-13 Tien-Ju Yang , Dhruv Guliani , Françoise Beaufays , Giovanni Motta

This paper proposes a highly compact, lightweight text-to-speech (TTS) model for on-device applications. To reduce the model size, the proposed model introduces two techniques. First, we introduce quantization-aware training (QAT), which…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Masaya Kawamura , Takuya Hasumi , Yuma Shirahata , Ryuichi Yamamoto

The DenseNet architecture is highly computationally efficient as a result of feature reuse. However, a naive DenseNet implementation can require a significant amount of GPU memory: If not properly managed, pre-activation batch normalization…

Computer Vision and Pattern Recognition · Computer Science 2017-07-24 Geoff Pleiss , Danlu Chen , Gao Huang , Tongcheng Li , Laurens van der Maaten , Kilian Q. Weinberger

Deploying quantized deep neural network (DNN) models with resource adaptation capabilities on ubiquitous Internet of Things (IoT) devices to provide high-quality AI services can leverage the benefits of compression and meet multi-scenario…

Machine Learning · Computer Science 2025-06-24 Jianhang Xie , Chuntao Ding , Xiaqing Li , Shenyuan Ren , Yidong Li , Zhichao Lu

Deep neural networks achieve outstanding results in challenging image classification tasks. However, the design of network topologies is a complex task and the research community makes a constant effort in discovering top-accuracy…

Machine Learning · Computer Science 2019-09-25 Florian Scheidegger , Luca Benini , Costas Bekas , Cristiano Malossi

Various hardware accelerators have been developed for energy-efficient and real-time inference of neural networks on edge devices. However, most training is done on high-performance GPUs or servers, and the huge memory and computing costs…

Hardware Architecture · Computer Science 2021-04-21 Kaiqi Zhang , Cole Hawkins , Xiyuan Zhang , Cong Hao , Zheng Zhang

This paper presents a comprehensive evaluation of lightweight deep learning models for image classification, emphasizing their suitability for deployment in resource-constrained environments such as low-memory devices. Five state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Tasnim Shahriar

Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study…

Computer Vision and Pattern Recognition · Computer Science 2019-12-10 Ji Lin , Chuang Gan , Song Han

Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during inference. We present LieQ Layer-wise information…

Machine Learning · Computer Science 2025-12-30 He Xiao , Qingyao Yang , Dirui Xie , Wendong Xu , Zunhai Su , Runming yang , Wenyong Zhou , Haobo Liu , Zhengwu Liu , Ngai Wong
‹ Prev 1 3 4 5 6 7 10 Next ›