We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has
been widely studied recently. A typical EDNN has multiple prediction heads at different …

Convolutional neural networks (CNNs) play an important role in today's mobile and edge
computing systems for vision-based tasks like object classification and detection. However …

Very deep neural networks lead to significantly better performance on various real tasks.
However, it usually causes slow inference and is hard to be deployed on real-world devices …

Many present and future problems associated with artificial intelligence are not due to its
limitations, but to our poor assessment of its behaviour. Our evaluation procedures produce …

Routine visual inspection is fundamental to the preventive maintenance of power
equipment. Convolutional neural networks (CNNs) substantially reduce the number of …

As AI systems become more complex and widespread, they require significant
computational power, increasing energy consumption. Addressing this challenge is …

Mixture of Experts (MoE) are rising in popularity as a means to train extremely large-scale
models, yet allowing for a reasonable computational cost at inference time. Recent state-of …

The article proposes model of human-centered and impact-oriented e-training course
development. Multi-actor, multi-sector and multidisciplinary co-creation is considered a key …

Artificial Intelligence has been developed for decades with the achievement of great
progress. Recently, deep learning shows its ability to solve many real world problems, eg …