Space-air-ground integrated networks (SAGINs) are key elements for facilitating high-speed
seamless connectivity to the devices/users in infrastructure-less environments, where the …

Processing-in-Memory (PIM) architectures have gained popularity due to their ability to
alleviate the memory wall by performing large numbers of operations within the memory …

Internet-of-Things (IoT) devices are becoming both intelligent and green. On the one hand,
Deep Neural Network (DNN) compression techniques make it possible to run deep learning …

Backing up the intermediate results of hardware-accelerated deep inference is crucial to
ensure the progress of execution on batteryless computing platforms. However, hardware …

We present INTERCEPT, a compile-time toolchain enabling manifold throughput
improvements when running intermittent DNN inference on IoT devices, in exchange of a …

There is an emerging requirement for performing data-intensive parallel computations, eg,
machine-learning inference, locally on batteryless sensors. These devices are resource …

To meet the growing demand for integrated circuits (ICs) in increasingly complex and
demanding applications, the semiconductor industry has evolved dramatically during the …

IoT systems can operate efficiently in scenarios with limited or sporadic power availability by
utilizing intermittent power sources, such as energy harvesting. Typical implementations are …

As global demand for computational power rises, driven by advancements in AI, big data,
and cloud computing, the energy consumption of computing systems is becoming a critical …

Processing In-Memory (PIM) based on emerging non-volatile memory technologies can
accelerate machine learning tasks even for batteryless devices operating intermittently …