Visual recognition is currently one of the most important and active research areas in
computer vision, pattern recognition, and even the general field of artificial intelligence. It …

Fire is one of the most frequent and common emergencies threatening public safety and
social development. Recently, intelligent fire detection technologies represented by …

A commonly cited inefficiency of neural network training by back-propagation is the update
locking problem: each layer must wait for the signal to propagate through the network before …

We introduce and study the problem of Online Continual Compression, where one attempts
to simultaneously learn to compress and store a representative dataset from a non iid data …

In time series classification and regression, signals are typically mapped into some
intermediate representation used for constructing models. Since the underlying task is often …

Experience and reasoning occur across multiple temporal scales: milliseconds, seconds,
hours or days. The vast majority of computer vision research, however, still focuses on …

Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. We propose to learn these filters as combinations of preset …

In this article, we propose a set of transform-based neural network layers as an alternative to
the 3 x 3 Conv2D layers in convolutional neural networks (CNNs). The proposed layers can …

Convolutional neural networks (CNNs) learn filters in order to capture local correlation
patterns in feature space. In contrast, in this paper we propose harmonic blocks that produce …

In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network
layer which we call DCT-perceptron to replace the $3\times3 $ Conv2D layers in the …