On-device learning faces memory constraints when optimizing or fine-tuning on edge devices with limited resources. Current techniques for training deep models on edge devices rely heavily on backpropagation. However, its high memory usage calls for a reassessment of its dominance.In this paper, we propose forward gradient descent (FGD) as a potential solution to overcome the memory capacity limitation in on-device learning. However, FGD's dependencies across layers hinder parallel computation and can lead to inefficient resource utilization.To mitigate this limitation, we propose AsyncFGD, an asynchronous framework that decouples dependencies, utilizes module-wise stale parameters, and maximizes parallel computation. We demonstrate its convergence to critical points through rigorous theoretical analysis.Empirical evaluations conducted on NVIDIA's AGX Orin, a popular embedded device, show that AsyncFGD reduces memory consumption and enhances hardware efficiency, offering a novel approach to on-device learning.

On-device learning promises collaborative training of machine learning models across edge devices without the sharing of user data. In state-of-the-art on-device learning algorithms, devices communicate their model weights over a decentralized communication network. Transmitting model weights requires huge communication overhead and means only devices with identical model architectures can be included. To overcome these limitations, we introduce a distributed distillation algorithm where devices communicate and learn from soft-decision (softmax) outputs, which are inherently architecture-agnostic and scale only with the number of classes. The communicated soft-decisions are each model's outputs on a public, unlabeled reference dataset, which serves as a common vocabulary between devices. We prove that our algorithm converges with probability 1 to a stationary point where all devices in the communication network distill the entire network's knowledge on the reference data, regardless of their local connections. Our analysis assumes smooth loss functions, which can be non-convex. Simulations support our theoretical findings and show that even a naive implementation of our algorithm significantly reduces the communication overhead while achieving an overall comparable performance to state-of-the-art, depending on the regime. By requiring little communication overhead and allowing for cross-architecture training, we remove two main obstacles to scaling on-device learning.

Tiny Machine Learning (TinyML) algorithms have seen extensive use in recent years, enabling wearable devices to be not only connected but also genuinely intelligent by running machine learning (ML) computations directly on-device. Among such devices, smart glasses have particularly benefited from TinyML advancements. TinyML facilitates the on-device execution of the inference phase of ML algorithms on embedded and wearable devices, and more recently, it has expanded into On-device Learning (ODL), which allows both inference and learning phases to occur directly on the device. The application of ODL techniques to wearable devices is particularly compelling, as it enables the development of more personalized models that adapt based on the data of the user. However, one of the major challenges of ODL algorithms is the scarcity of labeled data collected on-device. In smart wearable contexts, requiring users to manually label large amounts of data is often impractical and could lead to user disengagement with the technology. To address this issue, this paper explores the application of Active Learning (AL) techniques, i.e., techniques that aim at minimizing the labeling effort, by actively selecting from a large quantity of unlabeled data only a small subset to be labeled and added to the training set of the algorithm. In particular, we propose TActiLE, a novel AL algorithm that selects from the stream of on-device sensor data the ones that would help the ML algorithm improve the most once coupled with labels provided by the user. TActiLE is the first Active Learning technique specifically designed for the TinyML context. We evaluate its effectiveness and efficiency through experiments on multiple image classification datasets. The results demonstrate its suitability for tiny and wearable devices.

Existing work solves this problem by reducing the number of trainable parameters. However, this doesn't directly translate to memory saving since the major bottleneck is the activations, not parameters.

--Human activity recognition (HAR) is a research field that employs Machine Learning (ML) techniques to identify user activities. Recent studies have prioritized the development of HAR solutions directly executed on wearable devices, enabling the on-device activity recognition. This approach is supported by the Tiny Machine Learning (TinyML) paradigm, which integrates ML within embedded devices with limited resources. However, existing approaches in the field lack in the capability for on-device learning of new HAR tasks, particularly when supervised data are scarce. T o address this limitation, our paper introduces Dendron, a novel TinyML methodology designed to facilitate the on-device learning of new tasks for HAR, even in conditions of limited supervised data. Experimental results on two public-available datasets and an off-the-shelf device (STM32-NUCLEO-F401RE) show the effectiveness and efficiency of the proposed solution. I NTRODUCTION Human activity recognition (HAR) is a research area focusing on developing systems that can automatically identify user activities (e.g., lying, standing, walking, or running) by using Machine Learning (ML) techniques.

Additional Feedback: - the empirical results do not look very convincing: the performance of distributed distillation is significantly worse than plain distributed SGD. The amount of communication required is substantially smaller, but comparable gains have been reached by federated averaging with C 1 [3] or by dynamic averaging [4] with (seemingly) far better model performance (on a fully connected network graph, though). I suggest comparing to those baselines on a fully connected network. On a not-fully connected network I suggest comparing to decentralized learning approaches [5,6]. The authors might argue that this has an advantages over federated averaging for non-convex problems: in federated averaging, averaging two models in different minima can lead to a resulting model that is way worse than each of the two local models.

On-device learning faces memory constraints when optimizing or fine-tuning on edge devices with limited resources. Current techniques for training deep models on edge devices rely heavily on backpropagation. However, its high memory usage calls for a reassessment of its dominance.In this paper, we propose forward gradient descent (FGD) as a potential solution to overcome the memory capacity limitation in on-device learning. However, FGD's dependencies across layers hinder parallel computation and can lead to inefficient resource utilization.To mitigate this limitation, we propose AsyncFGD, an asynchronous framework that decouples dependencies, utilizes module-wise stale parameters, and maximizes parallel computation. We demonstrate its convergence to critical points through rigorous theoretical analysis.Empirical evaluations conducted on NVIDIA's AGX Orin, a popular embedded device, show that AsyncFGD reduces memory consumption and enhances hardware efficiency, offering a novel approach to on-device learning.

On-device learning promises collaborative training of machine learning models across edge devices without the sharing of user data. In state-of-the-art on-device learning algorithms, devices communicate their model weights over a decentralized communication network. Transmitting model weights requires huge communication overhead and means only devices with identical model architectures can be included. To overcome these limitations, we introduce a distributed distillation algorithm where devices communicate and learn from soft-decision (softmax) outputs, which are inherently architecture-agnostic and scale only with the number of classes. The communicated soft-decisions are each model's outputs on a public, unlabeled reference dataset, which serves as a common vocabulary between devices.

Electroencephalogram (EEG)-based Brain-Computer Interfaces (BCIs) have garnered significant interest across various domains, including rehabilitation and robotics. Despite advancements in neural network-based EEG decoding, maintaining performance across diverse user populations remains challenging due to feature distribution drift. This paper presents an effective approach to address this challenge by implementing a lightweight and efficient on-device learning engine for wearable motor imagery recognition. The proposed approach, applied to the well-established EEGNet architecture, enables real-time and accurate adaptation to EEG signals from unregistered users. Leveraging the newly released low-power parallel RISC-V-based processor, GAP9 from Greeenwaves, and the Physionet EEG Motor Imagery dataset, we demonstrate a remarkable accuracy gain of up to 7.31\% with respect to the baseline with a memory footprint of 15.6 KByte. Furthermore, by optimizing the input stream, we achieve enhanced real-time performance without compromising inference accuracy. Our tailored approach exhibits inference time of 14.9 ms and 0.76 mJ per single inference and 20 us and 0.83 uJ per single update during online training. These findings highlight the feasibility of our method for edge EEG devices as well as other battery-powered wearable AI systems suffering from subject-dependant feature distribution drift.

Miniaturized cyber-physical systems (CPSes) powered by tiny machine learning (TinyML), such as nano-drones, are becoming an increasingly attractive technology. Their small form factor (i.e., ~10cm diameter) ensures vast applicability, ranging from the exploration of narrow disaster scenarios to safe human-robot interaction. Simple electronics make these CPSes inexpensive, but strongly limit the computational, memory, and sensing resources available on board. In real-world applications, these limitations are further exacerbated by domain shift. This fundamental machine learning problem implies that model perception performance drops when moving from the training domain to a different deployment one. To cope with and mitigate this general problem, we present a novel on-device fine-tuning approach that relies only on the limited ultra-low power resources available aboard nano-drones. Then, to overcome the lack of ground-truth training labels aboard our CPS, we also employ a self-supervised method based on ego-motion consistency. Albeit our work builds on top of a specific real-world vision-based human pose estimation task, it is widely applicable for many embedded TinyML use cases. Our 512-image on-device training procedure is fully deployed aboard an ultra-low power GWT GAP9 System-on-Chip and requires only 1MB of memory while consuming as low as 19mW or running in just 510ms (at 38mW). Finally, we demonstrate the benefits of our on-device learning approach by field-testing our closed-loop CPS, showing a reduction in horizontal position error of up to 26% vs. a non-fine-tuned state-of-the-art baseline. In the most challenging never-seen-before environment, our on-device learning procedure makes the difference between succeeding or failing the mission.