Related papers: Fault Tolerance in Distributed Neural Computing

Data storage systems serve as the foundation of digital society. The enormous data generated by people on a daily basis make the fault tolerance of data storage systems increasingly important. Unfortunately, modern storage systems consist…

Existing distributed machine learning (DML) systems focus on improving the computational efficiency of distributed learning, whereas communication aspects have received less attention. Many DML systems treat the network as a blackbox. Thus,…

This short paper describes early experiments to validate the capabilities of a component-based platform to observe and control a software architecture in the small. This is part of a whole process for resilient computing, i.e. targeting the…

We introduce a class of distributed control policies for networks of discrete-time linear systems with polytopic additive disturbances. The objective is to restrict the network-level state and controls to user-specified polyhedral sets for…

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

In current scenario several commercial and social organizations are using computer networks for their business and management purposes. In order to meet the business requirements networks are also grow. The growth of network also promotes…

The recent decades have seen a surge of interests in distributed computing. Existing work focus primarily on either distributed computing platforms, data query tools, or, algorithms to divide big data and conquer at individual machines etc.…

In recent years, the application of artificial intelligence (AI) in wireless communications has demonstrated inherent robustness against wireless channel distortions. Most existing works empirically leverage this robustness to yield…

The recurrent neural network has been greatly developed for effectively solving time-varying problems corresponding to complex environments. However, limited by the way of centralized processing, the model performance is greatly affected by…

In this paper, we consider a network of processors aiming at cooperatively solving mixed-integer convex programs subject to uncertainty. Each node only knows a common cost function and its local uncertain constraint set. We propose a…

Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts…

Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the…

Dynamical systems are often time-varying, whose modeling requires a function that evolves with respect to time. Recent studies such as the neural ordinary differential equation proposed a time-dependent neural network, which provides a…

Erasure coding techniques are getting integrated in networked distributed storage systems as a way to provide fault-tolerance at the cost of less storage overhead than traditional replication. Redundancy is maintained over time through…

With the large-scale integration and use of neural network models, especially in critical embedded systems, their security assessment to guarantee their reliability is becoming an urgent need. More particularly, models deployed in embedded…

Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…

Integration of Inverter Based Resources (IBRs) which lack the intrinsic characteristics such as the inertial response of the traditional synchronous-generator (SG) based sources presents a new challenge in the form of analyzing the grid…

Fault tolerance is essential for building reliable services; however, it comes at the price of redundancy, mainly the "replication factor" and "diversity". With the increasing reliance on Internet-based services, more machines (mainly…

Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics. To reduce the residual risk for unexpected DNN behaviour and provide evidence for their trustworthy…

Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…