Kernel pruning methods have been proposed to speed up, simplify, and improve explanation of convolutional neural network (CNN) models. However, the effectiveness a simplified model is often below original one. In this letter, we present new based on objective subjective relevance criteria for kernel elimination in layer-by-layer fashion. During process, CNN retrained only when current layer ent...

Nowadays health is an essential factor in human life, among all the complexities brain tumors are very critical to deal with. Though there some existing techniques classify related deficiencies, no proper method segment process. MRI (Magnetic Resonance Imaging) and ultrasound vastly used order condition over world lately. But exist limitations those processes keenly tumor analysis, this segment...

This paper constitutes the novel hypergraph convolutional neural networkbased clustering technique. technique is employed to solve problem for Citeseer dataset and Cora dataset. Each contains feature matrix incidence of (i.e., constructed from matrix). method utilizes both matrices. Initially, auto-encoders are transform high dimensional space low space. In end, we apply k-means transformed mat...

A crop image classification using convolutional neural network is proposed in the paper. Classification of images important and required many applications such as yield prediction, decease detection etc. (Yang et al., 2020)(Kavitha 2022). The main challenges are availability large dataset extraction meaningful features to describe a class image(Barbedo, 2018). We have pre-trained models like VG...

High-resolution depth map can be inferred from a lowresolution one with the guidance of an additional highresolution texture map of the same scene. Recently, deep neural networks with large receptive fields are shown to benefit applications such as image completion. Our insight is that super resolution is similar to image completion, where only parts of the depth values are precisely known. In ...

Our goal is to classify 3D models directly using convolutional neural network. Most of existing approaches rely on a set of human-engineered features. We use 3D convolutional neural network to let the network learn the features over 3D space to minimize classification error. We trained and tested over ShapeNet dataset with data augmentation by applying random transformations. We made various vi...

Convolutional neural networks (CNN) have recently achieved remarkable performance in a wide range of applications. In this research, we equip convolutional sequence-to-sequence (seq2seq) model with an efficient graph linearization technique for abstract meaning representation parsing. Our linearization method is better than the prior method at signaling the turn of graph traveling. Additionally...

A dynamic neural network architecture based on the Time-Delay Neural Network and the Convolutional Neural Network is originated. The dynamic network achieves much better performance than those of MLP and TDNN when dealing with syllable recognition. Such performance is also comparable to that of the more popular HMM method.

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolut...