convolution

(redirected from convolutional)
Also found in: Dictionary, Thesaurus, Encyclopedia.

convolution

 [kon″vo-lu´shun]
a tortuous irregularity or elevation caused by the infolding of a structure upon itself.

con·vo·lu·tion

(kon'vō-lū'shŭn),
1. A coiling or rolling of an organ.
2. Specifically, a gyrus of the cerebral cotex or folia of the cerebellar cortex.
[L. convolutio]

convolution

(kŏn′və-lo͞o′shən)
n.
1. A form or part that is folded or coiled.
2. One of the convex folds of the surface of the brain.

con′vo·lu′tion·al adj.

convolution

(1) A redundancy or folding of tissue native to an organ. 
(2) Gyrus, brain.

convolution

An elevation on the surface of a structure and an infolding of the tissue upon itself

con·vo·lu·tion

(kon-vŏ-lū'shŭn)
1. A coiling or rolling of an organ.
2. Specifically, a gyrus of the cerebral or cerebellar cortex.
[L. convolutio]
References in periodicals archive ?
The architecture consists of two one-dimensional convolutional layers, each followed by a one-dimensional subsampling layer applying the maximization function and at the end one fully connected layer with an output layer.
It is obtained from an input image through a convolutional layer followed by ReLU and given to big gate (G).
Pooling is usually applied after a convolutional layer in order to reduce information size and to offer more invariability to rotations, translations, and small variation in features.
We use small-size 3 x 3 convolutional filters for all convolutional layers.
Convolutional neural networks known as complex neural networks have been applied to speech recognition, computer vision, audio translation to achieve what has been referred to as 'Deep learning." What is generically referred to as AI in the lay press and in medical and diagnostic imaging applications actually represents deep learning using neural networks to generate algorithms to make predictions.
To achieve the network output weights of the relative target points in training and conveniently design the convolutional network, we make 40 copies of the relative target points as the inputs; namely, the total inputs are 800 datasets.
Recently, the deep convolutional neural network (CNN) has been successfully used in pattern recognition (e.g., [6, 7]) and classification (e.g., [8, 9]).
As a classical model of the deep learning system, convolutional neural network (CNN) has an enormous advantage in image recognition [4].
At present, some tracking methods based on learning feature have been proposed, using convolutional networks trained offline [12,13].