Related papers: Temporal Patience: Efficient Adaptive Deep Learnin…

Nowadays, the deployment of deep learning models on edge devices for addressing real-world classification problems is becoming more prevalent. Moreover, there is a growing popularity in the approach of early classification, a technique that…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification.…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

In this paper, we study a network of distributed radar sensors that collaboratively perform sensing tasks by transmitting their quantized radar signals over capacity-constrained fronthaul links to a central unit for joint processing. We…

Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic.…

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

Neural networks rely on learning synaptic weights. However, this overlooks other neural parameters that can also be learned and may be utilized by the brain. One such parameter is the delay: the brain exhibits complex temporal dynamics with…

Deep learning (DL) models have emerged as a promising solution for the Internet of Things (IoT). However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and…

Although deep learning has made strides in the field of deep noise suppression, leveraging deep architectures on resource-constrained devices still proved challenging. Therefore, we present an early-exiting model based on nsNet2 that…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment…

Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring. Previous work has shown that Deep Learning (DL) can…

Advances in sensor technology and automation have ushered in an era of data abundance, where the ability to identify and extract relevant information in real time has become increasingly critical. Traditional filtering approaches, which…

Early Risk Detection (ERD) on the Web aims to identify promptly users facing social and health issues. Users are analyzed post-by-post, and it is necessary to guarantee correct and quick answers, which is particularly challenging in…

Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinson's disease. Classification performance is critical to identifying brain…

To enhance the resource scheduling performance of phased array radar, we propose a dynamic adaptive resource scheduling algorithm based on synthesis priorities and pulse interleaving. This approach addresses the challenges of low…

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…