-
PowerLinear Activation Functions with application to the first layer of CNNs
Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing. -
MisConv: Convolutional Neural Networks for Missing Data
Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like... -
SqueezeNet v1.1 and ZynqNet
The dataset used in this paper is the SqueezeNet v1.1 and ZynqNet CNNs, which are characterized by small model size and limited computational requirements. -
Very Deep Multilingual Convolutional Neural Networks for LVCSR
Convolutional neural networks (CNNs) are a standard component of many current state-of-the-art Large Vocabulary Continuous Speech Recognition (LVCSR) systems. However, CNNs in... -
R-CNN minus R
Deep convolutional neural networks (CNNs) have had a major impact in most areas of image understanding, including object category detection. -
ImageNet-1000
The dataset used in this paper is ImageNet-1000 pre-trained CNNs. -
A deep learning approach for person identification using ear biometrics
Ear recognition using CNNs.
