相关论文: A Machine Learning Pipeline Stage for Adaptive Fre…

Tasking machine learning to predict segments of a time series requires estimating the parameters of a ML model with input/output pairs from the time series. Using the equivalence between statistical data assimilation and supervised machine…

Federated Learning (FL) enables clients to share learning parameters instead of local data, reducing communication overhead. Traditional wireless networks face latency challenges with FL. In contrast, Cell-Free Massive MIMO (CFmMIMO) can…

Parameterizable machine learning (ML) accelerators are the product of recent breakthroughs in ML. To fully enable their design space exploration (DSE), we propose a physical-design-driven, learning-based prediction framework for…

Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML…

Thermoplastics injection molding allows the production of complex parts in large series. Industrial quality requirements are increasing. The injection molding process needs to be regulate in order to maintain a working point. There is…

Adaptive workloads can change on--the--fly the configuration of their jobs, in terms of number of processes. In order to carry out these job reconfigurations, we have designed a methodology which enables a job to communicate with the…

In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers…

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server…

Support for Machine Learning (ML) applications in networks has significantly improved over the last decade. The availability of public datasets and programmable switching fabrics (including low-level languages to program them) present a…

The learning rate is one of the most important hyper-parameters for model training and generalization. However, current hand-designed parametric learning rate schedules offer limited flexibility and the predefined schedule may not match the…

Training machine learning (ML) algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from…

The provision of social care applications is crucial for elderly people to improve their quality of life and enables operators to provide early interventions. Accurate predictions of user dropouts in healthy ageing applications are…

Machine learning (ML) pipeline composition and optimisation have been studied to seek multi-stage ML models, i.e. preprocessor-inclusive, that are both valid and well-performing. These processes typically require the design and traversal of…

This paper proposes a neural framework for power and timing prediction of multi-stage data path, distinguishing itself from traditional lib-based analytical methods dependent on driver characterization and load simplifications. To the best…

Today's evolving power system contains an increasing amount of power electronic interfaced energy sources and loads that require a paradigm shift in utility operations. Sub-synchronous oscillations at frequencies around 13-15 Hz, for…

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the…

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Quantum optimal control is a promising approach to improve the accuracy of quantum gates, but it relies on complex algorithms to determine the best control settings. CPU or GPU-based approaches often have delays that are too long to be…

Recent trends in networking are proposing the use of Machine Learning (ML) techniques for the control and operation of the network. In this context, ML can be used as a computer network modeling technique to build models that estimate the…

Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by functional checking. This is insufficient for practical RTL…