Classification of abnormal children: Discrimination learning ability

AbstractClassical ethology and behavioral ecology did not pay much attention to learning. However, studies of social learning in nature reviewed here reveal the near-ubiquity of reliance on social information for skill acquisition by developing birds and mammals. This conclusion strengthens the plausibility of the cultural intelligence hypothesis for the evolution of intelligence, which assumes that selection on social learning abilities automatically improves individual learning ability. Thus, intelligent species will generally be cultural species. Direct tests of the cultural intelligence hypothesis require good estimates of the amount and kind of social learning taking place in nature in a broad variety of species. These estimates are lacking so far. Here, we start the process of developing a functional classification of social learning, in the form of the social learning spectrum, which should help to predict the mechanisms of social learning involved. Once validated, the categories can be used to estimate the cognitive demands of social learning in the wild.

Download Full-text

Deep Feature Fusion with Integration of Residual Connection and Attention Model for Classification of VHR Remote Sensing Images

Remote Sensing ◽

10.3390/rs11131617 ◽

2019 ◽

Vol 11 (13) ◽

pp. 1617 ◽

Cited By ~ 5

Author(s):

Jicheng Wang ◽

Li Shen ◽

Wenfan Qiao ◽

Yanshuai Dai ◽

Zhilin Li

Keyword(s):

Remote Sensing ◽

Feature Fusion ◽

Learning Ability ◽

Remote Sensing Images ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Attention Model ◽

Low Level ◽

Deep Feature

The classification of very-high-resolution (VHR) remote sensing images is essential in many applications. However, high intraclass and low interclass variations in these kinds of images pose serious challenges. Fully convolutional network (FCN) models, which benefit from a powerful feature learning ability, have shown impressive performance and great potential. Nevertheless, only classification results with coarse resolution can be obtained from the original FCN method. Deep feature fusion is often employed to improve the resolution of outputs. Existing strategies for such fusion are not capable of properly utilizing the low-level features and considering the importance of features at different scales. This paper proposes a novel, end-to-end, fully convolutional network to integrate a multiconnection ResNet model and a class-specific attention model into a unified framework to overcome these problems. The former fuses multilevel deep features without introducing any redundant information from low-level features. The latter can learn the contributions from different features of each geo-object at each scale. Extensive experiments on two open datasets indicate that the proposed method can achieve class-specific scale-adaptive classification results and it outperforms other state-of-the-art methods. The results were submitted to the International Society for Photogrammetry and Remote Sensing (ISPRS) online contest for comparison with more than 50 other methods. The results indicate that the proposed method (ID: SWJ_2) ranks #1 in terms of overall accuracy, even though no additional digital surface model (DSM) data that were offered by ISPRS were used and no postprocessing was applied.

Download Full-text

Deletion of hippocalcin impairs NMDA-induced CREB phosphorylation in the hippocampus and visual discrimination learning ability

Neuroscience Research ◽

10.1016/s0168-0102(00)80903-7 ◽

2000 ◽

Vol 38 ◽

pp. S9

Author(s):

K Takamatsu

Keyword(s):

Discrimination Learning ◽

Visual Discrimination ◽

Learning Ability ◽

Creb Phosphorylation ◽

Visual Discrimination Learning

Download Full-text

Inheritance of discrimination learning ability and retention in BA and DBA mice

Behavior Genetics ◽

10.1007/bf01065628 ◽

1981 ◽

Vol 11 (2) ◽

pp. 173-177 ◽

Cited By ~ 1

Author(s):

J. H. F. van Abeelen ◽

T. M. P. Schetgens

Keyword(s):

Discrimination Learning ◽

Learning Ability

Download Full-text

Residual Dense Network Based on Channel-Spatial Attention for the Scene Classification of a High-Resolution Remote Sensing Image

Remote Sensing ◽

10.3390/rs12111887 ◽

2020 ◽

Vol 12 (11) ◽

pp. 1887 ◽

Cited By ~ 5

Author(s):

Xiaolei Zhao ◽

Jing Zhang ◽

Jimiao Tian ◽

Li Zhuo ◽

Jie Zhang

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Spatial Attention ◽

Remote Sensing Image ◽

Learning Ability ◽

Aerial Image ◽

Dense Network ◽

Scene Classification ◽

Training Requirements

The scene classification of a remote sensing image has been widely used in various fields as an important task of understanding the content of a remote sensing image. Specially, a high-resolution remote sensing scene contains rich information and complex content. Considering that the scene content in a remote sensing image is very tight to the spatial relationship characteristics, how to design an effective feature extraction network directly decides the quality of classification by fully mining the spatial information in a high-resolution remote sensing image. In recent years, convolutional neural networks (CNNs) have achieved excellent performance in remote sensing image classification, especially the residual dense network (RDN) as one of the representative networks of CNN, which shows a stronger feature learning ability as it fully utilizes all the convolutional layer information. Therefore, we design an RDN based on channel-spatial attention for scene classification of a high-resolution remote sensing image. First, multi-layer convolutional features are fused with residual dense blocks. Then, a channel-spatial attention module is added to obtain more effective feature representation. Finally, softmax classifier is applied to classify the scene after adopting data augmentation strategy for meeting the training requirements of the network parameters. Five experiments are conducted on the UC Merced Land-Use Dataset (UCM) and Aerial Image Dataset (AID), and the competitive results demonstrate that our method can extract more effective features and is more conducive to classifying a scene.

Download Full-text

The Automatic Classification of ECG Based on BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.121-122.111 ◽

2010 ◽

Vol 121-122 ◽

pp. 111-116 ◽

Cited By ~ 1

Author(s):

Lan Lan Yu ◽

Bo Xue Tan ◽

Tian Xing Meng

Keyword(s):

Neural Network ◽

Clinical Application ◽

Bp Neural Network ◽

Heart Diseases ◽

Automatic Classification ◽

Learning Ability ◽

The Neural Network ◽

Heart Beating ◽

Recognition Level

The classification and recognition of ECG are helpful to distinguish and diagnose heart diseases, which also have very important clinical application value for the automatic diagnoses of ECG. The traditional recognition methods need people to extract determinant rules and have no learning ability so that they are unable to simulate the intuition and fuzzy diagnoses function used by doctor very well. The neural network technology has strongpoint of self-organization, self-learning and strong tolerance for error. It provides a new method for the automatic classification of ECG. In this paper, we use BP neural network to do automatic classification for five kinds of ECG which are natural stylebook, paced heart beating, left branch block, right branch block and ventricular tachycardia. The average recognition level is 98.1%. Experiment results show that the neural networ k technology can greatly improve the recognition level of ECG. It has good clinical application value.

Download Full-text

Plant Leaf Classification using Convolutional Neural Network

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813999200904162029 ◽

2020 ◽

Vol 13 ◽

Author(s):

Nidhi ◽

Jay Kant Pratap Singh Yadav

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Image Data ◽

Learning Ability ◽

Training Time ◽

Automatic Feature Extraction ◽

Computer Vision Applications ◽

Shape Characteristics ◽

And Training

Introduction: Convolutional Neural Network (CNNet) has proven the indispensable system in order to perform the recognition and classification tasks in different computer vision applications. The purpose of this study is to exploit the marvelous learning ability of CNNet in the image classification field. Method: In order to circumvent the overfitting issues and to enhance the generalization potential of the proposed FLCNNet, augmentation has been performed on the Flavia dataset that impose translation and rotation techniques to perform the augmentation with the transformed leaves having the same labels as the original ones. Both the classification models executed using; one without augmentation and one with the augmentation data are compared to check the effectiveness of the augmentation hence the aim of the proposed work. Moreover, Edge detection technique has been applied to extract the shape of the leaf images, in order to classify them accordingly. Thereafter, the FLCNNet is trained and tested for the dataset, with and without augmentation. Results: The results are gathered in terms of accuracy and training time for both datasets. The Augmented dataset (dataset 2) has been found effective and more feasible for classification without misguiding the network to learn (avoid overfitting) as compared to the dataset without augmentation (dataset 1). Conclusion: This paper proposed the Five Layer Convolution Neural Network (FLCNNet) method to classify plant leaves based on their shape. This approach can classify 8 types of leaves using automatic feature extraction, by utilizing their shape characteristics. To avoid the overfitting condition and make the performance better. We aimed to perform the classification of the augmented leaf dataset. Discussion: We proposed a five Layer CNNet (FLCNNet) to classify the leaf image data into different classes or labels based on the shape characteristics of the leaves.

Download Full-text

A Study on Human Learning Ability during Classification of Motion and Colour Visual Cues and Their Combination

Cybernetics and Information Technologies ◽

10.2478/cait-2021-0006 ◽

2021 ◽

Vol 21 (1) ◽

pp. 73-86

Author(s):

Albena Tchamova ◽

Jean Dezert ◽

Nadejda Bocheva ◽

Pavlina Konstantinova ◽

Bilyana Genova ◽

...

Keyword(s):

Visual Cues ◽

Human Learning ◽

Learning Curves ◽

Learning Ability ◽

Stimulus Information ◽

Relevant Stimulus ◽

Group Behaviour ◽

Human Individual ◽

Effect Of Age

Abstract The paper presents a study on the human learning process during the classification of stimuli, defined by motion and color visual cues and their combination. Because the classification dimension and the features that define each category are uncertain, we model the learning curves using Bayesian inference and more precisely the Normalized Conjunctive Consensus rule, and also on the base of the more efficient probabilistic Proportional Conflict Redistribution rule No 5 (pPCR5) defined within Dezert-Smarandache Theory (DSmT) of plausible and paradoxical reasoning. Our goal is to study how these rules succeed to model consistently both: human individual and group behaviour during the learning of the associations between the stimuli and the responses in categorization tasks varying by the amount of relevant stimulus information. The effect of age on this process is also evaluated.

Download Full-text