Enhancing object, action, and effect recognition using probabilistic affordances

2019 ◽  
Vol 27 (5) ◽  
pp. 295-306
Author(s):  
Esteban Jaramillo-Cabrera ◽  
Eduardo F Morales ◽  
Jose Martinez-Carranza
Keyword(s):  
Neural Networks ◽  
High Performance ◽  
Recognition Performance ◽  
Action Planning ◽  
Classification Performance ◽  
Training Data ◽  
Missing Information ◽  
Classification Tasks ◽  
Combining Information ◽  
Very High

Recent advances in deep learning, in particular in convolutional neural networks (CNNs), have been widely used in robotics for object classification and action recognition, among others, with very high performance. Nevertheless, this high performance, mostly in classification tasks, is rarely accompanied by reasoning processes that consider the relationships between objects, actions, and effects. In this article, we used three CNNs to classify objects, actions, and effects that were trained with the CERTH-SOR3D dataset that has more than 20,000 RGB-D videos. This dataset involves 14 objects, 13 actions, and in this article was augmented with seven effects. The probabilistic vector output of each trained CNN was combined into a Bayesian network (BN) to capture the relationships between objects, actions, and effects. It is shown that by probabilistically combining information from the three classifiers, it is possible to improve the classification performance of each CNN or to level the same performance with less training data. In particular, the recognition performance improved from 71.2% to 79.7% for actions, 85.0%–86.7% for objects, and 77.0%–82.1% for effects. In the article, it is also shown that with missing information, the model can still produce reasonable classification performance. In particular, the system can be used for reasoning purposes in robotics, as it can make action planning with information from object and effects or it can predict effects with information from objects and actions.

scholarly journals Brain hierarchy score: Which deep neural networks are hierarchically brain-like?

2020 ◽  
Author(s):  
Soma Nonaka ◽  
Kei Majima ◽  
Shuntaro C. Aoki ◽  
Yukiyasu Kamitani
Keyword(s):  
Neural Networks ◽  
Image Recognition ◽  
High Performance ◽  
Deep Neural Networks ◽  
Recognition Performance ◽  
Brain Activity ◽  
Spatial Integration ◽  
Hierarchical Processing ◽  
Visual Areas ◽  
The Brain

SummaryAchievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on the decoding of individual DNN unit activations from human brain activity. We find that BH scores for 29 pretrained DNNs with varying architectures are negatively correlated with image recognition performance, indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that relatively simple feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method provides new ways for designing DNNs and understanding the brain in consideration of their representational homology.

Heart Disease Classification Using Artificial Neural Networks

2015 ◽  
Vol 781 ◽  
pp. 624-627 ◽  
Author(s):  
Rati Wongsathan ◽  
Pasit Pothong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Heart Disease ◽  
Classification Accuracy ◽  
High Performance ◽  
Disease Classification ◽  
Generalized Regression Neural Network ◽  
The Neural Networks ◽  
Very High

Neural Networks (NNs) has emerged as an importance tool for classification in the field of decision making. The main objective of this work is to design the structure and select the optimized parameter in the neural networks to implement the heart disease classifier. Three types of neural networks, i.e. Multi-layered Perceptron Neural Network (MLP-NN), Radial Basis Function Neural Networks (RBF-NN), and Generalized Regression Neural Network (GR-NN) have been used to test the performance of heart disease classification. The classification accuracy obtained by RBFNN gave a very high performance than MLP-NN and GR-NN respectively. The performance of accuracy is very promising compared with the previously reported another type of neural networks.

scholarly journals Discriminative non-negative representation based classifier for image recognition

2021 ◽  
Vol 15 ◽  
pp. 174830262110449
Author(s):  
Kai-Jun Hu ◽  
He-Feng Yin ◽  
Jun Sun
Keyword(s):  
Pattern Classification ◽  
State Of The Art ◽  
Source Code ◽  
Classification Performance ◽  
Training Data ◽  
Practical Applications ◽  
The Past ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Negative Representation

During the past decade, representation based classification method has received considerable attention in the community of pattern recognition. The recently proposed non-negative representation based classifier achieved superb recognition results in diverse pattern classification tasks. Unfortunately, discriminative information of training data is not fully exploited in non-negative representation based classifier, which undermines its classification performance in practical applications. To address this problem, we introduce a decorrelation regularizer into the formulation of non-negative representation based classifier and propose a discriminative non-negative representation based classifier for pattern classification. The decorrelation regularizer is able to reduce the correlation of representation results of different classes, thus promoting the competition among them. Experimental results on benchmark datasets validate the efficacy of the proposed discriminative non-negative representation based classifier, and it can outperform some state-of-the-art deep learning based methods. The source code of our proposed discriminative non-negative representation based classifier is accessible at https://github.com/yinhefeng/DNRC .

scholarly journals Independent Random Recurrent Neural Networks for Infrared Spatial Point Targets Classification

2019 ◽  
Vol 9 (21) ◽  
pp. 4622 ◽  
Author(s):  
Wu ◽  
Lu ◽  
Hu ◽  
Zhao
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Radiation Intensity ◽  
Infrared Radiation ◽  
Classification Problem ◽  
Classification Performance ◽  
Surveillance Systems ◽  
Spatial Point ◽  
Classification Tasks ◽  
Comprehensive Classification

Exo-atmospheric infrared (IR) point target discrimination is an important research topic of space surveillance systems. It is difficult to describe the characteristic information of the shape and micro-motion states of the targets and to discriminate different targets effectively by the characteristic information. This paper has constructed the infrared signature model of spatial point targets and obtained the infrared radiation intensity sequences dataset of different types of targets. This paper aims to design an algorithm for the classification problem of infrared radiation intensity sequences of spatial point targets. Recurrent neural networks (RNNs) are widely used in time series classification tasks, but face several problems such as gradient vanishing and explosion, etc. In view of shortcomings of RNNs, this paper proposes an independent random recurrent neural network (IRRNN) model, which combines independent structure RNNs with randomly weighted RNNs. Without increasing the training complexity of network learning, our model solves the problem of gradient vanishing and explosion, improves the ability to process long sequences, and enhances the comprehensive classification performance of the algorithm effectively. Experiments show that the IRRNN algorithm performs well in classification tasks and is robust to noise.

scholarly journals Recognition of Handwritten Arabic and Hindi Numerals Using Convolutional Neural Networks

2021 ◽  
Vol 11 (4) ◽  
pp. 1573
Author(s):  
Amin Alqudah ◽  
Ali Mohammad Alqudah ◽  
Hiam Alquran ◽  
Hussein R. Al-Zoubi ◽  
Mohammed Al-Qodah ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
High Performance ◽  
Recognition Rate ◽  
Second Stage ◽  
The Past ◽  
The World ◽  
Very High ◽  
Handwritten Arabic

Arabic and Hindi handwritten numeral detection and classification is one of the most popular fields in the automation research. It has many applications in different fields. Automatic detection and automatic classification of handwritten numerals have persistently received attention from researchers around the world due to the robotic revolution in the past decades. Therefore, many great efforts and contributions have been made to provide highly accurate detection and classification methodologies with high performance. In this paper, we propose a two-stage methodology for the detection and classification of Arabic and Hindi handwritten numerals. The classification was based on convolutional neural networks (CNNs). The first stage of the methodology is the detection of the input numeral to be either Arabic or Hindi. The second stage is to detect the input numeral according to the language it came from. The simulation results show very high performance; the recognition rate was close to 100%.

scholarly journals Prototype generation in the string space via approximate median for data reduction in nearest neighbor classification

2021 ◽  
Author(s):  
Francisco J. Castellanos ◽  
Jose J. Valero-Mas ◽  
Jorge Calvo-Zaragoza
Keyword(s):  
Data Reduction ◽  
High Performance ◽  
Nearest Neighbor ◽  
Structural Data ◽  
Classification Performance ◽  
Training Data ◽  
Complex Structural ◽  
Low Efficiency ◽  
Definition Of ◽  
The Cost

AbstractThe k-nearest neighbor (kNN) rule is one of the best-known distance-based classifiers, and is usually associated with high performance and versatility as it requires only the definition of a dissimilarity measure. Nevertheless, kNN is also coupled with low-efficiency levels since, for each new query, the algorithm must carry out an exhaustive search of the training data, and this drawback is much more relevant when considering complex structural representations, such as graphs, trees or strings, owing to the cost of the dissimilarity metrics. This issue has generally been tackled through the use of data reduction (DR) techniques, which reduce the size of the reference set, but the complexity of structural data has historically limited their application in the aforementioned scenarios. A DR algorithm denominated as reduction through homogeneous clusters (RHC) has recently been adapted to string representations but as obtaining the exact median value of a set of string data is known to be computationally difficult, its authors resorted to computing the set-median value. Under the premise that a more exact median value may be beneficial in this context, we, therefore, present a new adaptation of the RHC algorithm for string data, in which an approximate median computation is carried out. The results obtained show significant improvements when compared to those of the set-median version of the algorithm, in terms of both classification performance and reduction rates.

scholarly journals Explainable Neural Network Ensembles

2021 ◽  
Author(s):  
Manomita Chakraborty ◽  
Saroj Kumar Biswas ◽  
Biswajit Purkayastha
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
Decision Rules ◽  
Rule Extraction ◽  
Classification Performance ◽  
Classification Rules ◽  
Multiple Networks ◽  
Neural Network Ensembles ◽  
Network Ensembles

Abstract Neural networks are known for providing impressive classification performance, and the ensemble learning technique is further acting as a catalyst to enhance this performance by integrating multiple networks. But like neural networks, neural network ensembles are also considered as a black-box because they cannot explain their decision making process. So, despite having high classification performance, neural networks and their ensembles are not suited for some applications which require explainable decisions. However, the rule extraction technique can overcome this drawback by representing the knowledge learned by a neural network in the guise of interpretable decision rules. A rule extraction algorithm provides neural networks with the power to justify their classification responses through explainable classification rules. Several rule extraction algorithms exist to extract classification rules from neural networks, but only a few of them generates rules using neural network ensembles. So this paper proposes an algorithm named Rule Extraction using Ensemble of Neural Network Ensembles (RE-E-NNES) to demonstrate the high performance of neural network ensembles through rule extraction. RE-E-NNES extracts classification rules by ensembling several neural network ensembles. Results show the efficacy of the proposed RE-E-NNES algorithm compared to different existing rule extraction algorithms.

scholarly journals Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery

2020 ◽  
Vol 12 (2) ◽  
pp. 207 ◽  
Author(s):  
Sherrie Wang ◽  
William Chen ◽  
Sang Michael Xie ◽  
George Azzari ◽  
David B. Lobell
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Damage Assessment ◽  
High Performance ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Classification Performance ◽  
Support Vector ◽  
Weak Supervision ◽  
Weakly Supervised

Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful translation to remote sensing tasks has been limited by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain. In this work, we perform cropland segmentation using two types of labels commonly found in remote sensing datasets that can be considered sources of “weak supervision”: (1) labels comprised of single geotagged points and (2) image-level labels. We demonstrate that (1) a U-Net trained on a single labeled pixel per image and (2) a U-Net image classifier transferred to segmentation can outperform pixel-level algorithms such as logistic regression, support vector machine, and random forest. While the high performance of neural networks is well-established for large datasets, our experiments indicate that U-Nets trained on weak labels outperform baseline methods with as few as 100 labels. Neural networks, therefore, can combine superior classification performance with efficient label usage, and allow pixel-level labels to be obtained from image labels.

scholarly journals Regularizing Fully Convolutional Networks for Time Series Classification by Decorrelating Filters

2019 ◽  
Vol 33 ◽  
pp. 10003-10004 ◽  
Author(s):  
Kaushal Paneri ◽  
Vishnu TV ◽  
Pankaj Malhotra ◽  
Lovekesh Vig ◽  
Gautam Shroff
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Deep Neural Networks ◽  
Training Data ◽  
Time Series Classification ◽  
Strong Correlations ◽  
Average Correlation ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Classification Tasks

Deep neural networks are prone to overfitting, especially in small training data regimes. Often, these networks are overparameterized and the resulting learned weights tend to have strong correlations. However, convolutional networks in general, and fully convolution neural networks (FCNs) in particular, have been shown to be relatively parameter efficient, and have recently been successfully applied to time series classification tasks. In this paper, we investigate the application of different regularizers on the correlation between the learned convolutional filters in FCNs using Batch Normalization (BN) as a regularizer for time series classification (TSC) tasks. Results demonstrate that despite orthogonal initialization of the filters, the average correlation across filters (especially for filters in higher layers) tends to increase as training proceeds, indicating redundancy of filters. To mitigate this redundancy, we propose a strong regularizer, using simple yet effective filter decorrelation. Our proposed method yields significant gains in classification accuracy for 44 diverse time series datasets from the UCR TSC benchmark repository.

Daily Discharge Prediction Using Artificial Neural Networks

2010 ◽  
Vol 29-32 ◽  
pp. 2799-2803
Author(s):  
Wei Guo Zhao ◽  
Li Ying Wang
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Training Data ◽  
Global Minima ◽  
Discharge Data ◽  
Forecasting System ◽  
Daily Discharge ◽  
Artificial Neural ◽  
Very High

A daily discharge prediction system is developed by the Artificial Neural Networks (ANN) using real daily discharge data, ANN have great generalization ability and guarantee global minima for given training data. In the paper, with 8 years long-term daily information, the ANN can construct a very high precision daily discharge forecasting system. The experiment shows that the predicted curve well regresses the observed curve. It can be concluded that this technique can be seen as a very promising option to solve nonlinear regression.

Sign in / Sign up

Export Citation Format

Share Document