convolution


Also found in: Dictionary, Thesaurus, Medical, Encyclopedia, Wikipedia.
Related to convolution: Fourier transform, Convolution theorem
References in periodicals archive ?
Based on convolution pose machine (CPM) [1], we propose a Convolution Machine of Pose which incorporates with multiple stages, multiple layer based feature maps, various receptive fields and scalable region of interest.
Ailyn Agonia DOHA ART can transform society, so it has to be taken seriously, said renowned Iraqi sculptor and painter Ala Bashir at the opening of his exhibition titled 'Shade of Convolution' at the Al Markhiya Gallery of Doha Fire Station on Tuesday.
This model architecture differs from traditional models because it uses no fully-connected layers, instead relying completely on convolution and upsampling operations.
It combines analogue convolution during the readout process; fast column-parallel processing for image analysis and feature extraction, including analogue storage and software-defined analogue-to-digital (A/D) converters; an asynchronous readout path for sparse data compression; and an application-specific instruction set processor (ASIP) concept for software-defined process control.
The first is the Titchmarsh Convolution Theorem, which characterizes the null spaces of Volterra convolution operators.
These techniques revealed an interactive relationship, known as a mathematical convolution, among two cultural dimensions that was otherwise masked by the independent variables used.
The researchers overcame this by using a method they call 'partial convolution.' The method essentially does another pass-on edited portions of an image and renormalizes them to look as clean as possible.
These methods contain convolution neural network- (CNN-) based models [9, 10] and generative adversarial network-based models (GAN) [11, 12].
The experimental group adopts an artificial neural network (ANN) method, including convolution neural networks (CNN) and recurrent neural network (RNN) methods.
In 2013, Brian Kingsbury, researcher of IBM, and several other persons [16] took the logarithmic Mel filter coefficient as the input of deep convolution network and further extracted the "original" features (Mel filter coefficient), and the experiment shows that the recognition rate has a relative increase of 13-30% compared to the traditional Gaussian mixed model and has a relative increase of 4-12% compared to deep neural networks.
The encoder network used here consists of convolution layers of 64 filters, each of size 3 x 3, manually padded, followed by batch normalization and ReLu activation unit and repeatedly followed by same convolution, batch normalization, and ReLu for proper downsampling and robust feature extraction.
Compared with the conventional NN, the architecture of the deep CNN consists of several alternations of convolution and pooling layers, which is an analog of the receptive field.