Related papers: Logical Synchrony Networks: A formal model for det…
In cloud computing, software-defined network (SDN) gaining more attention due to its advantages in network configuration to improve network performance and network monitoring. SDN addresses an issue of static architecture in traditional…
Kahn process networks are a model of computation based on a collection of sequential, deterministic processes that communicate by sending messages through unbounded channels. They are well suited for modelling stream-based computations, but…
Recurrent neural networks (RNNs) have emerged as an effective representation of control policies in sequential decision-making problems. However, a major drawback in the application of RNN-based policies is the difficulty in providing…
Deep-learning models such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) have been successfully used for process-mining tasks. They have achieved better performance for different predictive tasks than traditional…
Software-defined networking (SDN) is a novel paradigm that out-sources the control of packet-forwarding switches to a set of software controllers. The most fundamental task of these controllers is the correct implementation of the…
This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference in the light of noisy data samples, then passed as input…
The evolution of 5G and Beyond networks has enabled new applications with stringent end-to-end latency requirements, but providing reliable low-latency service with high throughput over public wireless networks is still a significant…
Despite prior advances in PINNs, significant challenges remain in localized solid mechanics problems because of the limitations of single network formulations in simultaneous resolution of smooth global responses and near-tip singularities,…
We present a new CSP- and SAT-based approach for coordinating interfaces of distributed stream-connected components provided as closed-source services. The Kahn Process Network (KPN) is taken as a formal model of computation and a Message…
This paper investigates two prominent probabilistic neural modeling paradigms: Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression. While BNNs incorporate epistemic uncertainty by…
Networked mission-critical applications (e.g., avionic control and industrial automation systems) require deterministic packet transmissions to support a range of sensing and control tasks with stringent timing constraints. While…
We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose weights…
In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP) for non-vision…
With 5G networking, deterministic guarantees are emerging as a key enabler. In this context, we present a scalable Damper-based architecture for Large-scale Deterministic IP Networks (D-LDN) that meets required bounds on end-to-end delay…
The emerging paradigm of resource disaggregation enables the deployment of cloud-like services across a pool of physical and virtualized resources, interconnected using a network fabric. This design embodies several benefits in terms of…
We introduce Controlled Stochastic Activity Networks (Controlled SANs), a formal extension of classical Stochastic Activity Networks that integrates explicit control actions into a unified semantic framework for modeling distributed…
Existing model-based processes for embedded real-time systems support the analysis of various non-functional properties, most notably schedulability, through model checking, simulation or other means. The analysis results are then used for…
The ubiquity of neural networks (NNs) in real-world applications, from healthcare to natural language processing, underscores their immense utility in capturing complex relationships within high-dimensional data. However, NNs come with…
In distributed ML applications, shared parameters are usually replicated among computing nodes to minimize network overhead. Therefore, proper consistency model must be carefully chosen to ensure algorithm's correctness and provide high…
This paper provides a comprehensive survey of queueing and scheduling mechanisms for supporting large scale deterministic networks (LDNs). The survey finds that extensive mechanism design research and standards development for LDNs has been…