Related papers: Cross-Layer Effects on Training Neural Algorithms …

The exponential growth of data storage demands has necessitated the evolution of hierarchical storage management strategies [1]. This study explores the application of streaming machine learning [3] to revolutionize data prefetching within…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally…

Policy gradient reinforcement learning (RL) algorithms have achieved impressive performance in challenging learning tasks such as continuous control, but suffer from high sample complexity. Experience replay is a commonly used approach to…

HTTP video streaming is in wide use to deliver video over the Internet. With HTTP adaptive steaming, a video playback dynamically selects a video stream from a pre-encoded representation based on available bandwidth and viewport (screen)…

The main task of HTTP Adaptive Streaming is to adapt video quality dynamically under variable network conditions. This is a key feature for multimedia delivery especially when quality of service cannot be granted network-wide and, e.g.,…

The social metaverse is a growing digital ecosystem that blends virtual and physical worlds. It allows users to interact socially, work, shop, and enjoy entertainment. However, privacy remains a major challenge, as immersive interactions…

HTTP adaptive streaming (HAS) has become the universal technology for video streaming over the Internet. Many HAS system designs aim at sharing the network bandwidth in a rate-fair manner. However, rate fairness is in general not equivalent…

Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…

We study the problem of spectrum sharing between goal-oriented (GO) and legacy data-oriented (DO) systems. For the former, data quality and representation is no longer optimized based on classical communication key performance indicators,…

Mobile cyberphysical systems have received considerable attention over the last decade, as communication, computing and control come together on a common platform. Understanding the complex interactions that govern the behavior of large…

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their…

With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) to utilize…

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small…

Computer-science-oriented artificial neural networks (ANNs) have achieved tremendous success in a variety of scenarios via powerful feature extraction and high-precision data operations. It is well known, however, that ANNs usually suffer…

The movement of large quantities of data during the training of a Deep Neural Network presents immense challenges for machine learning workloads. To minimize this overhead, especially on the movement and calculation of gradient information,…

While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the…

A majority of recent developments in neural architecture search (NAS) have been aimed at decreasing the computational cost of various techniques without affecting their final performance. Towards this goal, several low-fidelity and…

The Asynchronous Transfer Mode (ATM) network is crucial due to its ability to efficiently transmit data, provide reliable connections, and support various service classes with specific Quality of Service (QoS) requirements. In this paper,…

Burst contention is a well-known challenging problem in Optical Burst Switching (OBS) networks. Deflection routing is used to resolve contention. Burst retransmission is used to reduce the Burst Loss Ratio (BLR) by retransmitting dropped…