Related papers: Reconfigurable Broadcast Networks and Asynchronous…

State-space models (SSMs) and transformers dominate the language modeling landscape. However, they are constrained to a lower computational complexity than classical recurrent neural networks (RNNs), limiting their expressivity. In…

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…

As AI systems grow increasingly specialized and complex, managing hardware heterogeneity becomes a pressing challenge. How can we efficiently coordinate and synchronize heterogeneous hardware resources to achieve high utilization? How can…

We study the complexity of the model-checking problem for parameterized discrete-timed systems with arbitrarily many anonymous and identical processes, with and without a distinguished "controller", and communicating via synchronous…

Simulating a shared register can mask the intricacies of designing algorithms for asynchronous message-passing systems subject to crash failures, since it allows them to run algorithms designed for the simpler shared-memory model. Typically…

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…

Wireless Sensor Networks (WSN) are used by many industries from environment monitoring systems to NASA's space exploration programs, as it has allowed society to monitor and prevent problems before they occur with less cost and maintenance.…

Long short-term memory recurrent neural networks (LSTM-RNNs) are considered state-of-the art in many speech processing tasks. The recurrence in the network, in principle, allows any input to be remembered for an indefinite time, a feature…

A new neural network architecture (PSCNN) is developed to improve performance and speed of such networks. The architecture has all the advantages of the previous models such as self-organization and possesses some other superior…

Systems such as sensor networks and teams of autonomous robots consist of multiple autonomous entities that interact with each other in a distributed, asynchronous manner. These entities need to keep track of the state of the system as it…

We consider synchronous distributed systems in which anonymous processors communicate by shared read-write variables. The goal is to have all the processors assign unique names to themselves. We consider the instances of this problem…

Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid State Machine (LSM) is a bio-inspired RC model that mimics the cortical microcircuits and uses spiking neural networks…

We are proposing fully parallel and maximally distributed hardware realization of a generic neuro-computing system. More specifically, the proposal relates to the wireless sensor networks technology to serve as a massively parallel and…

With the rising number of interconnected devices and sensors, modeling distributed sensor networks is of increasing interest. Recurrent neural networks (RNN) are considered particularly well suited for modeling sensory and streaming data.…

Recurrent neural networks (RNNs) have drawn interest from machine learning researchers because of their effectiveness at preserving past inputs for time-varying data processing tasks. To understand the success and limitations of RNNs, it is…

Restricted Boltzmann Machines (RBMs) offer a versatile architecture for unsupervised machine learning that can in principle approximate any target probability distribution with arbitrary accuracy. However, the RBM model is usually not…

The performance of large-scale computing systems often critically depends on high-performance communication networks. Dynamically reconfigurable topologies, e.g., based on optical circuit switches, are emerging as an innovative new…

We present Broadcast by Balanced Saturation (BBS), a general broadcast algorithm designed to optimize communication efficiency across diverse network topologies. BBS maximizes node utilization, addressing challenges in broadcast operations…

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…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…