scholarly journals ETALON IMAGES: UNDERSTANDING THE CONVOLUTION NEURAL NETWORKS

2018 ◽  
Vol XLII-2 ◽  
pp. 707-714 ◽  
Author(s):  
V. V. Molchanov ◽  
B. V. Vishnyakov ◽  
V. S. Gorbatsevich ◽  
Y. V. Vizilter
Keyword(s):  
Neural Networks ◽  
Input Image ◽  
Neural Net ◽  
Convolution Neural Networks ◽  
Affine Maps ◽  
Specific Input ◽  
Current Input ◽  
High Level ◽  
The Way

In this paper we propose a new technic called etalons, which allows us to interpret the way how convolution network makes its predictions. This mechanism is very similar to voting among different experts. Thereby CNN could be interpreted as a variety of experts, but it acts not like a sum or product of them, but rather represent a complicated hierarchy. We implement algorithm for etalon acquisition based on well-known properties of affine maps. We show that neural net has two high-level mechanisms of voting: first, based on attention to input image regions, specific to current input, and second, based on ignoring specific input regions. We also make an assumption that there is a connection between complexity of the underlying data manifold and the number of etalon images and their quality.

scholarly journals Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural Networks

2021 ◽  
Author(s):  
Colin Conwell ◽  
Fenil Doshi ◽  
George Alvarez
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Human Subjects ◽  
Neural Net ◽  
Feature Representations ◽  
Wide Range ◽  
Intuitive Physics ◽  
Feed Forward Neural Networks ◽  
The Stability ◽  
High Level

At a glance, the human visual system transforms complex retinal images into generic feature representations useful for guiding a wide range of behaviors. Here, we provide evidence that the feature representations embedded in purely feed- forward neural networks are sufficient to explain seemingly high-level human judgments: in this case, the stability of randomly arranged block towers. To do this, we first show that we can linearly decode stability from the features of two deep neural networks – a supervised network trained on ImageNet, and a varia- tional autoencoder trained only to reconstruct images of block towers from various perspectives – neither of which were ever taught stability per se. We then derive a set of image-computable features to use as predictors of performance, finding that the stability judgments of both human subjects and the neural net decoders are best predicted by the same feature. Our findings suggest overall that at least some aspects of seemingly higher-level reasoning in a now paradigmatic intuitive physics task may be grounded in direct readouts of purely perceptual features.

The machine training in problems of satellite images’s processing

Metrologiya ◽  
2020 ◽  
pp. 15-37
Author(s):  
L. P. Bass ◽  
Yu. A. Plastinin ◽  
I. Yu. Skryabysheva
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Satellite Images ◽  
Vision Systems ◽  
Earth Remote Sensing ◽  
Practical Applications ◽  
Convolution Neural Networks ◽  
Computer Vision Systems ◽  
Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks

2017 ◽  
Vol 6 (4) ◽  
pp. 15
Author(s):  
JANARDHAN CHIDADALA ◽  
RAMANAIAH K.V. ◽  
BABULU K ◽  
◽  
◽  
...  
Keyword(s):  
Neural Networks ◽  
Super Resolution ◽  
Convolution Neural Networks ◽  
Novel Approach ◽  
Image Super Resolution

Convolution Neural Networks for Traffic Sign Classification

2019 ◽  
Author(s):  
Rajashekar A ◽  
Shruti Hegdekar ◽  
Dikpal Shrestha ◽  
Prabin Nepal ◽  
Sujanb Neupane
Keyword(s):  
Neural Networks ◽  
Traffic Sign ◽  
Convolution Neural Networks ◽  
Traffic Sign Classification

scholarly journals Interpretation of Swedish Sign Language Using Convolutional Neural Networks and Transfer Learning

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Gustaf Halvardsson ◽  
Johanna Peterson ◽  
César Soto-Valero ◽  
Benoit Baudry
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Web Application ◽  
Training Dataset ◽  
Motion Processing ◽  
Image Perception ◽  
Sign Languages ◽  
High Level

AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.

Sign in / Sign up

Export Citation Format

Share Document