Energy consumption of memory accesses dominates the compute energy in
en...
Due to complex interactions among various deep neural network (DNN)
opti...
Processing-In-Memory (PIM) accelerators have the potential to efficientl...
Exploration tasks are essential to many emerging robotics applications,
...
Video conferencing systems suffer from poor user experience when network...
Through a series of federal initiatives and orders, the U.S. Government ...
In recent years, many accelerators have been proposed to efficiently pro...
Vision Transformer (ViT) demonstrates that Transformer for natural langu...
Neural architecture search (NAS) typically consists of three main steps:...
Depth information is useful for many applications. Active depth sensors ...
This paper describes various design considerations for deep neural netwo...
Exploration tasks are embedded in many robotics applications, such as se...
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
Depth sensing is a critical function for robotic tasks such as localizat...
We present a single-shot, bottom-up approach for whole image parsing. Wh...
This paper presents Navion, an energy-efficient accelerator for
visual-i...
The design of DNNs has increasingly focused on reducing the computationa...
This work proposes an automated algorithm, called NetAdapt, that adapts ...
Deep neural networks (DNNs) are currently widely used for many artificia...
Computer vision enables a wide range of applications in robotics/drones,...
Machine learning plays a critical role in extracting meaningful informat...
Deep convolutional neural networks (CNNs) are indispensable to
state-of-...
This paper presents a programmable, energy-efficient and real-time objec...
State-of-the-art super-resolution (SR) algorithms require significant
co...