… An important advantage of convolutional neural networks is the ease with which they can
be implemented in hardware. Specialized analog/digital chips have been designed and used …

… convolutional neural network (CNN). A CNN is composed of different types of layers, such as
convolutional … These deep neural networks were also successfully applied to reinforcement …

… network specific to a problem. In this work, we have done a thorough literature survey of
Convolutional Neural Networks … work in Convolutional Neural Networks by LeCun et al. In 1990 […

… In this paper, we focus on the use of very deep convolutional neural networks for sentence
classification tasks. Applying similar ideas to other sequence processing tasks, in particular …

… application of convolutional neural networks to vision … convolutional neural network and
not a superior stereo method. We verify this claim by replacing the convolutional neural network …

… Training large neural networks can take weeks, or even months. … We consider convolutional
neural networks (CNNs) used for … to approximate weights of a convolutional neural network. …

… First, we introduce a very deep convolutional network architecture with up to 14 weight …
The very deep convolutional networks we describe here are adaptations of the VGG Net …

… pen trajectory; a replicated convolutional neural network that spots and recognizes characters;
and a Hidden Markov Model (HMM) that interprets the networks output by taking word-…

… previously published convolutional neural networks and they … depths” was shown for
convolutional neural networks in NLP. … use of very deep convolutional neural networks for …

… Micheli [55] proposed the first graph convolution neural network based on spatial domain,
called neural network for graphs (NN4G). … LeCun, “Very deep multilingual convolutional neural …