Related papers: DAPA: Distribution Aware Piecewise Activation Func…
The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge…
The continuous aperture array (CAPA) can provide higher degree-of-freedom and spatial resolution than the spatially discrete array (SDPA), where optimizing multi-user current distributions in CAPA systems is crucial but challenging. The…
The advent of switches with programmable dataplanes has enabled the rapid development of new network functionality, as well as providing a platform for acceleration of a broad range of application-level functionality. However, existing…
The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models. There are several commonly used simple nonlinear functions, including Rectified Linear Unit (ReLU) and Leaky-ReLU…
The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron. However, deciding on the best activation is non-trivial, and the choice depends on the architecture,…
Accurate engagement estimation is essential for adaptive human-computer interaction systems, yet robust deployment is hindered by poor generalizability across diverse domains and challenges in modeling complex interaction dynamics.To tackle…
Task failures in prior fine-grained robotic manipulation methods often stem from suboptimal initial grasping, which is critical for subsequent manipulation and reducing the requirement for complex pose adjustments. To address this, we…
Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build…
In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped…
Active Voltage Control (AVC) on the Power Distribution Networks (PDNs) aims to stabilize the voltage levels to ensure efficient and reliable operation of power systems. With the increasing integration of distributed energy resources, recent…
The deployment of Vision Transformers (ViTs) on hardware platforms, specially Field-Programmable Gate Arrays (FPGAs), presents many challenges, which are mainly due to the substantial computational and power requirements of their non-linear…
A variety of computing platform like Field Programmable Gate Array (FPGA), Graphics Processing Unit (GPU) and multicore Central Processing Unit (CPU) in data centers are suitable for acceleration of data-intensive workloads. Especially,…
Feature attribution is essential for interpreting deep learning models, particularly in time-series domains such as healthcare, biometrics, and human-AI interaction. However, standard attribution methods, such as Integrated Gradients or…
Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges which utilizes a cluster to train a model in parallel.…
Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often…
Despite the increasing adoption of Field-Programmable Gate Arrays (FPGAs) in compute clouds, there remains a significant gap in programming tools and abstractions which can leverage network-connected, cloud-scale, multi-die FPGAs to…
Splitting the inference model between device, edge server, and cloud can improve the performance of EI greatly. Additionally, the non-orthogonal multiple access (NOMA), which is the key supporting technologies of B5G/6G, can achieve massive…
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In…
Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to label its desired samples. Traditional AL algorithms…
We consider the problem of maximizing the alpha-fairness utility over the downlink of a heterogeneous wireless network (HetNet) by jointly optimizing the association of users to transmission points (TPs) and the activation fractions of all…