Resource-efficient Convolutional Neural Networks (CNNs) are gaining more attention.
These CNNs have relatively low computational and memory requirements. A common …

Seeking the “sweet spot” in the accuracy-efficiency trade-off is increasing the heterogeneity
of state-of-the-art Convolutional Neural Networks (CNNs). Such CNN models exhibit …

Machine learning (ML) accelerators have been studied and used extensively to compute ML
models with high performance and low power. However, designing such accelerators …

3D reconstruction from videos has become increasingly popular for various applications,
including navigation for autonomous driving of robots and drones, augmented reality (AR) …

Since the lightweight convolutional neural network EfficientNet was proposed by Google in
2019, the series of models have quickly become very popular due to their superior …

A number of fast accumulation (FACCU) designs are proposed for one of the essential
components in DSP systems, the accumulator, to largely boost the DSP's maximum …

Deep neural networks (DNNs) with various nonlinear activation functions (NAFs) have
achieved unprecedented successes, sparking interest in efficient DNN hardware …

State-of-the-art compact models such as MobileNets and EfficientNets are structured using a
linear bottleneck and inverted residuals. Hardware architecture using a single dataflow …

With the development of lightweight convolutional neural networks (CNNs), these newly
proposed networks are more powerful than previous conventional models [,] and can be well …

During the early years following the AlexNet breakthrough [24], researchers have mainly
focused on designing Convolutional Neural Networks (CNNs) with higher accuracy [17, 47 …