Related papers: Training on the Fly: On-device Self-supervised Lea…
Communication efficiency in federated learning (FL) remains a critical challenge for resource-constrained environments. While prototype-based FL reduces communication overhead by sharing class prototypes-mean activations in the penultimate…
Machine learning (ML) empowers biomedical systems with the capability to optimize their performance through modeling of the available data extremely well, without using strong assumptions about the modeled system. Especially in nano-scale…
Unsupervised pre-training approaches have achieved great success in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and so on. However, compared to typical deep learning models, pre-training or even fine-tuning…
This paper presents a simulation platform, namely CIMulator, for quantifying the efficacy of various synaptic devices in neuromorphic accelerators for different neural network architectures. Nonvolatile memory devices, such as resistive…
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…
Neuromorphic Multiply-And-Accumulate (MAC) circuits utilizing synaptic weight elements based on SRAM or novel Non-Volatile Memories (NVMs) provide a promising approach for highly efficient hardware representations of neural networks. NVM…
Running machine learning inference on tiny devices, known as TinyML, is an emerging research area. This task requires generating inference code that uses memory frugally, a task that standard ML frameworks are ill-suited for. A deployment…
On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-tuning existing models and continually acquiring new tasks…
Nano-sized unmanned aerial vehicles (UAVs) are well-fit for indoor applications and for close proximity to humans. To enable autonomy, the nano-UAV must be able to self-localize in its operating environment. This is a…
On-device training is currently the most common approach for training machine learning (ML) models on private, distributed user data. Despite this, on-device training has several drawbacks: (1) most user devices are too small to train large…
Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled,…
Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems. Within this field, physics-informed neural networks (PINNs) and deep operator networks (DeepONets)…
Accelerating the inference of a trained DNN is a well studied subject. In this paper we switch the focus to the training of DNNs. The training phase is compute intensive, demands complicated data communication, and contains multiple levels…
Microfluidic devices offer numerous advantages in medical applications, including the capture of single cells in microwell-based platforms for genomic analysis. As the cost of sequencing decreases, the demand for high-throughput single-cell…
Human activity recognition (HAR) holds immense potential for transforming health and fitness monitoring, yet challenges persist in achieving personalized outcomes and sustainability for on-device continuous inferences. This work introduces…
Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that…
Deep Learning (DL) has shown impressive performance in many mobile applications. Most existing works have focused on reducing the computational and resource overheads of running Deep Neural Networks (DNN) inference on resource-constrained…
On-device intelligence is gaining significant attention recently as it offers local data processing and low power consumption. In this research, an on-device training circuitry for threshold-current memristors integrated in a crossbar…
We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the…
We showcase the practicability of an indoor positioning system (IPS) solely based on Neural Networks (NNs) and the channel state information (CSI) of a (Massive) multiple-input multiple-output (MIMO) communication system, i.e., only build…