Related papers: PEERNet: An End-to-End Profiling Tool for Real-Tim…

Fast and accurate predictions for complex physical dynamics are a significant challenge across various applications. Real-time prediction on resource-constrained hardware is even more crucial in real-world problems. The deep operator…

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in…

With the rapid development of AI hardware accelerators, applying deep learning-based algorithms to solve various low-level vision tasks on mobile devices has gradually become possible. However, two main problems still need to be solved:…

In this article, we evaluate the first experience of computation offloading from drones to real fifth-generation (5G) operator systems, including commercial and private carrier-grade 5G networks. A follow-me drone service was implemented as…

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely…

The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point…

With the rapid advancement of devices requiring intensive computation, such as Internet of Things (IoT) devices, smart sensors, and wearable technology, the computational demands on individual platforms with limited resources have…

Embedded distributed inference of Neural Networks has emerged as a promising approach for deploying machine-learning models on resource-constrained devices in an efficient and scalable manner. The inference task is distributed across a…

The increased presence of advanced sensors on the production floors has led to the collection of datasets that can provide significant insights into machine health. An important and reliable indicator of machine health, vibration signal…

Performance of end-to-end neural networks on a given hardware platform is a function of its compute and memory signature, which in-turn, is governed by a wide range of parameters such as topology size, primitives used, framework used,…

Neural networks are increasingly used as fast surrogate models across various domains, but unconstrained predictions can violate physical, operational, or safety requirements. We propose SnareNet, a feasibility-controlled architecture to…

Collaborative edge computing (CEC) is an emerging paradigm for heterogeneous devices to collaborate on edge computation jobs. For congestible links and computing units, delay-optimal forwarding and offloading for service chain tasks (e.g.,…

Supporting convolutional neural network (CNN) inference on resource-constrained IoT devices in a timely manner has been an outstanding challenge for emerging smart systems. To mitigate the burden on IoT devices, the prevailing solution is…

Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has…

Robot navigation systems are critical for various real-world applications such as delivery services, hospital logistics, and warehouse management. Although classical navigation methods provide interpretability, they rely heavily on expert…

Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution. It is already a complex process because of the…

This paper studies the design of self-adjusting networks whose topology dynamically adapts to the workload, in an online and demand-aware manner. This problem is motivated by emerging optical technologies which allow to reconfigure the…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

The proliferation of sensors over the last years has generated large amounts of raw data, forming data streams that need to be processed. In many cases, cloud resources are used for such processing, exploiting their flexibility, but these…

Several recent works show impressive results in mapping language-based human commands and image scene observations to direct robot executable policies (e.g., pick and place poses). However, these approaches do not consider the uncertainty…