Related papers: Self-DANA: A Resource-Efficient Channel-Adaptive S…

In natural language processing (NLP), the "Transformer" architecture was proposed as the first transduction model replying entirely on self-attention mechanisms without using sequence-aligned recurrent neural networks (RNNs) or convolution,…

The proliferation of GPU accelerated edge devices like Nvidia Jetsons and the rise in privacy concerns are placing an emphasis on concurrent DNN training and inferencing on edge devices. Inference and training have different computing and…

Recently, FCNs have attracted widespread attention in the CD field. In pursuit of better CD performance, it has become a tendency to design deeper and more complicated FCNs, which inevitably brings about huge numbers of parameters and an…

Video understanding typically requires fine-tuning the large backbone when adapting to new domains. In this paper, we leverage the egocentric video foundation models (Ego-VFMs) based on video-language pre-training and propose a…

Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming…

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the…

Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices. DNN surgery, which partitions DNN processing between mobile devices and multi-access edge computing (MEC) servers, can…

Embedded Field-Programmable Gate Arrays (eFPGAs) allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget compared with traditional FPGA platforms. However, the limited eFPGA logic and…

Automated analysis of electroencephalography (EEG) has recently undergone a paradigm shift. The introduction of transformer architectures and self-supervised pretraining (SSL) has led to the development of EEG foundation models. These…

This research studies an adaptive neural network with a Dynamic Classifier Selection framework on Field-Programmable Gate Arrays (FPGAs). The evaluations are conducted across three different datasets. By adjusting parameters, the…

We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding…

Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require…

The label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

The large models, as predicted by scaling raw forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the…

Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…

Machine-learning force fields can deliver accurate molecular dynamics (MD) at high computational cost. For SO(3)-equivariant models such as MACE, there is little systematic evidence on whether reduced-precision arithmetic and GPU-optimized…

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

Neural network (NN) potentials are a natural choice for coarse-grained (CG) models. Their many-body capacity allows highly accurate approximations of the potential of mean force, promising CG simulations at unprecedented accuracy. CG NN…

Resource-constrained devices are increasingly the deployment targets of machine learning applications. Static models, however, do not always suffice for dynamic environments. On-device training of models allows for quick adaptability to new…