Related papers: Reconfigurable Broadcast Networks and Asynchronous…

Resource allocation is an essential design aspect for current systems and bandwidth allocation is an essential design aspect in multi-protocol label switched and OpenFlow/SDN network infrastructures. The bandwidth allocation models (BAMs)…

We study the problem of privately emulating shared memory in message-passing networks. The system includes clients that store and retrieve replicated information on N servers, out of which e are malicious. When a client access a malicious…

We compare the solvability of the Consensus and Broadcast problems in synchronous communication networks in which the delivery of messages is not reliable. The failure model is the mobile omission faults model. During each round, some…

Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on long…

The bisimulation metric (BSM) is a powerful tool for analyzing state similarities within a Markov decision process (MDP), revealing that states closer in BSM have more similar optimal value functions. While BSM has been successfully…

Active replication following the state machine replication (SMR) approach is a way to make existing systems and services more reliable and fault-tolerant. The additional communication overhead has a negative impact on the system's…

In this article, we present a novel approach for block-structured adaptive mesh refinement (AMR) that is suitable for extreme-scale parallelism. All data structures are designed such that the size of the meta data in each distributed…

This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from…

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

We investigate the minimal number of failures that can partition a system where processes communicate both through shared memory and by message passing. We prove that this number precisely captures the resilience that can be achieved by…

The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is among the best parametric Text-to-Speech (TTS) systems in terms of the naturalness of generated speech, especially the naturalness in prosody. However, the model complexity…

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

Known as low energy consumption networks, spiking neural networks (SNNs) have gained a lot of attention within the past decades. While SNNs are increasing competitive with artificial neural networks (ANNs) for vision tasks, they are rarely…

Consensus and Broadcast are two fundamental problems in distributed computing, whose solutions have several applications. Intuitively, Consensus should be no harder than Broadcast, and this can be rigorously established in several models.…

The problem of learning a computational model from examples has been receiving growing attention. For the particularly challenging problem of learning models of distributed systems, existing results are restricted to models with a fixed…

We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a…

Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to scaling. This has led to the dominance of parallelizable…

With the increasing development of neuromorphic platforms and their related software tools as well as the increasing scale of spiking neural network (SNN) models, there is a pressure for interoperable and scalable representations of network…

Biological neurons communicate with a sparing exchange of pulses - spikes. It is an open question how real spiking neurons produce the kind of powerful neural computation that is possible with deep artificial neural networks, using only so…