scholarly journals Persistent self-supervised learning: From stereo to monocular vision for obstacle avoidance

2018 ◽  
Vol 10 (2) ◽  
pp. 186-206 ◽  
Author(s):  
Kevin van Hecke ◽  
Guido de Croon ◽  
Laurens van der Maaten ◽  
Daniel Hennes ◽  
Dario Izzo
Keyword(s):  
Supervised Learning ◽  
Stereo Vision ◽  
Large Data ◽  
Monocular Vision ◽  
Training Data ◽  
Data Sets ◽  
Learning Approaches ◽  
Robust Learning ◽  
Flying Robot ◽  
First Time

Self-supervised learning is a reliable learning mechanism in which a robot uses an original, trusted sensor cue for training to recognize an additional, complementary sensor cue. We study for the first time in self-supervised learning how a robot’s learning behavior should be organized, so that the robot can keep performing its task in the case that the original cue becomes unavailable. We study this persistent form of self-supervised learning in the context of a flying robot that has to avoid obstacles based on distance estimates from the visual cue of stereo vision. Over time it will learn to also estimate distances based on monocular appearance cues. A strategy is introduced that has the robot switch from flight based on stereo to flight based on monocular vision, with stereo vision purely used as “training wheels” to avoid imminent collisions. This strategy is shown to be an effective approach to the “feedback-induced data bias” problem as also experienced in learning from demonstration. Both simulations and real-world experiments with a stereo vision equipped ARDrone2 show the feasibility of this approach, with the robot successfully using monocular vision to avoid obstacles in a 5 × 5 m room. The experiments show the potential of persistent self-supervised learning as a robust learning approach to enhance the capabilities of robots. Moreover, the abundant training data coming from the own sensors allow to gather large data sets necessary for deep learning approaches.

scholarly journals Enhancing Image Diagnosis by the Implementation of Transfer Classifiers

2019 ◽  
Vol 8 (3) ◽  
pp. 999-1002
Keyword(s):  
Supervised Learning ◽  
Transfer Learning ◽  
Training Data ◽  
Data Sets ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Image Diagnosis ◽  
Sensitivity Problem ◽  
Common Application ◽  
Target Data

Images generated from a variety of sources and foundations today can pose difficulty for a user to interpret similarity in them or analyze them for further use because of their segmentation policies. This unconventionality can generate many errors, because of which the previously used traditional methodologies such as supervised learning techniques less resourceful, which requires huge quantity of labelled training data which mirrors the desired target data. This paper thus puts forward the mechanism of an alternative technique i.e. transfer learning to be used in image diagnosis so that efficiency and accuracy among images can be achieved. This type of mechanism deals with variation in the desired and actual data used for training and the outlier sensitivity, which ultimately enhances the predictions by giving better results in various areas, thus leaving the traditional methodologies behind. The following analysis further discusses about three types of transfer classifiers which can be applied using only small volume of training data sets and their contrast with the traditional method which requires huge quantities of training data having attributes with slight changes. The three different separators were compared amongst them and also together from the traditional methodology being used for a very common application used in our daily life. Also, commonly occurring problems such as the outlier sensitivity problem were taken into consideration and measures were taken to recognise and improvise them. On further research it was observed that the performance of transfer learning exceeds that of the conventional supervised learning approaches being used for small amount of characteristic training data provided reducing the stratification errors to a great extent

scholarly journals Text Classification Using Ensemble Of Non-Linear Support Vector Machines

2019 ◽  
Vol 8 (10) ◽  
pp. 3169-3174
Keyword(s):  
Support Vector Machines ◽  
Large Data ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Data Sets ◽  
Learning Approaches ◽  
Automatic Tagging ◽  
Vector Machines

With the advent of digital era, billions of the documents generate every day that need to be managed, processed and classified. Enormous size of text data is available on world wide web and other sources. As a first step of managing this mammoth data is the classification of available documents in right categories. Supervised machine learning approaches try to solve the problem of document classification but working on large data sets of heterogeneous classes is a big challenge. Automatic tagging and classification of the text document is a useful task due to its many potential applications such as classifying emails into spam or non-spam categories, news articles into political, entertainment, stock market, sports news, etc. The paper proposes a novel approach for classifying the text into known classes using an ensemble of refined Support Vector Machines. The advantage of proposed technique is that it can considerably reduce the size of the training data by adopting dimensionality reduction as pre-training step. The proposed technique has been used on three bench-marked data sets namely CMU Dataset, 20 Newsgroups Dataset, and Classic Dataset. Experimental results show that proposed approach is more accurate and efficient as compared to other state-of-the-art methods.

scholarly journals Discovering Latent Class Labels for Multi-Label Learning

2020 ◽  
Author(s):  
Jun Huang ◽  
Linchuan Xu ◽  
Jing Wang ◽  
Lei Feng ◽  
Kenji Yamanishi
Keyword(s):  
Large Scale ◽  
Latent Class ◽  
Training Data ◽  
Data Sets ◽  
Robust Learning ◽  
Large Scale Data ◽  
Novel Approach ◽  
Fixed Set ◽  
Class Labels ◽  
Scale Data

Existing multi-label learning (MLL) approaches mainly assume all the labels are observed and construct classification models with a fixed set of target labels (known labels). However, in some real applications, multiple latent labels may exist outside this set and hide in the data, especially for large-scale data sets. Discovering and exploring the latent labels hidden in the data may not only find interesting knowledge but also help us to build a more robust learning model. In this paper, a novel approach named DLCL (i.e., Discovering Latent Class Labels for MLL) is proposed which can not only discover the latent labels in the training data but also predict new instances with the latent and known labels simultaneously. Extensive experiments show a competitive performance of DLCL against other state-of-the-art MLL approaches.

Deep Learning Approaches for Sentiment Analysis Challenges and Future Issues

2022 ◽  
pp. 27-50
Author(s):  
Rajalaxmi Prabhu B. ◽  
Seema S.
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Model Building ◽  
Large Data ◽  
Machine Learning Algorithms ◽  
Large Data Sets ◽  
Data Sets ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Important Challenge

A lot of user-generated data is available these days from huge platforms, blogs, websites, and other review sites. These data are usually unstructured. Analyzing sentiments from these data automatically is considered an important challenge. Several machine learning algorithms are implemented to check the opinions from large data sets. A lot of research has been undergone in understanding machine learning approaches to analyze sentiments. Machine learning mainly depends on the data required for model building, and hence, suitable feature exactions techniques also need to be carried. In this chapter, several deep learning approaches, its challenges, and future issues will be addressed. Deep learning techniques are considered important in predicting the sentiments of users. This chapter aims to analyze the deep-learning techniques for predicting sentiments and understanding the importance of several approaches for mining opinions and determining sentiment polarity.

scholarly journals BUILDING GENERALIZATION USING DEEP LEARNING

2018 ◽  
Vol XLII-4 ◽  
pp. 565-572 ◽  
Author(s):  
M. Sester ◽  
Y. Feng ◽  
F. Thiemann
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Physical Reality ◽  
Training Data ◽  
Data Sets ◽  
Learning Approaches ◽  
Depth Analysis ◽  
Map Series ◽  
Training Examples ◽  
Future Work

<p><strong>Abstract.</strong> Cartographic generalization is a problem, which poses interesting challenges to automation. Whereas plenty of algorithms have been developed for the different sub-problems of generalization (e.g. simplification, displacement, aggregation), there are still cases, which are not generalized adequately or in a satisfactory way. The main problem is the interplay between different operators. In those cases the benchmark is the human operator, who is able to design an aesthetic and correct representation of the physical reality.</p><p>Deep Learning methods have shown tremendous success for interpretation problems for which algorithmic methods have deficits. A prominent example is the classification and interpretation of images, where deep learning approaches outperform the traditional computer vision methods. In both domains &amp;ndash; computer vision and cartography &amp;ndash; humans are able to produce a solution; a prerequisite for this is, that there is the possibility to generate many training examples for the different cases. Thus, the idea in this paper is to employ Deep Learning for cartographic generalizations tasks, especially for the task of building generalization. An advantage of this task is the fact that many training data sets are available from given map series. The approach is a first attempt using an existing network.</p><p>In the paper, the details of the implementation will be reported, together with an in depth analysis of the results. An outlook on future work will be given.</p>

scholarly journals Implementation of Supervised Learning towards Optimizing Queries in Database Systems

2019 ◽  
Vol 9 (2) ◽  
pp. 1182-1187
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Student Loans ◽  
Large Data ◽  
Database Systems ◽  
Large Data Sets ◽  
Data Sets ◽  
Human Intervention ◽  
Huge Data ◽  
Future Direction

Machine learning is a technology which with accumulated data provides better decisions towards future applications. It is also the scientific study of algorithms implemented efficiently to perform a specific task without using explicit instructions. It may also be viewed as a subset of artificial intelligence in which it may be linked with the ability to automatically learn and improve from experience without being explicitly programmed. Its primary intention is to allow the computers learn automatically and produce more accurate results in order to identify profitable opportunities. Combining machine learning with AI and cognitive technologies can make it even more effective in processing large volumes human intervention or assistance and adjust actions accordingly. It may enable analyzing the huge data of information. It may also be linked to algorithm driven study towards improving the performance of the tasks. In such scenario, the techniques can be applied to judge and predict large data sets. The paper concerns the mechanism of supervised learning in the database systems, which would be self driven as well as secure. Also the citation of an organization dealing with student loans has been presented. The paper ends discussion, future direction and conclusion.

scholarly journals An Improved Fellegi-Sunter Framework for Probabilistic Record Linkage Between Large Data Sets

2020 ◽  
Vol 36 (4) ◽  
pp. 803-825
Author(s):  
Marco Fortini
Keyword(s):  
Record Linkage ◽  
Large Data ◽  
Real Data ◽  
Large Data Sets ◽  
Training Data ◽  
Data Sets ◽  
Estimated Parameters ◽  
Unbiased Estimates ◽  
Structural Zeros ◽  
Different Sources

AbstractRecord linkage addresses the problem of identifying pairs of records coming from different sources and referred to the same unit of interest. Fellegi and Sunter propose an optimal statistical test in order to assign the match status to the candidate pairs, in which the needed parameters are obtained through EM algorithm directly applied to the set of candidate pairs, without recourse to training data. However, this procedure has a quadratic complexity as the two lists to be matched grow. In addition, a large bias of EM-estimated parameters is also produced in this case, so that the problem is tackled by reducing the set of candidate pairs through filtering methods such as blocking. Unfortunately, the probability that excluded pairs would be actually true-matches cannot be assessed through such methods.The present work proposes an efficient approach in which the comparison of records between lists are minimised while the EM estimates are modified by modelling tables with structural zeros in order to obtain unbiased estimates of the parameters. Improvement achieved by the suggested method is shown by means of simulations and an application based on real data.

scholarly journals Deep residual detection of radio frequency interference for FAST

2020 ◽  
Vol 492 (1) ◽  
pp. 1421-1431 ◽  
Author(s):  
Zhicheng Yang ◽  
Ce Yu ◽  
Jian Xiao ◽  
Bo Zhang
Keyword(s):  
Radio Frequency ◽  
Large Data ◽  
High Sensitivity ◽  
Original Data ◽  
Training Data ◽  
Radio Frequency Interference ◽  
Data Sets ◽  
Data Set ◽  
Time Required ◽  
Key Steps

ABSTRACT Radio frequency interference (RFI) detection and excision are key steps in the data-processing pipeline of the Five-hundred-meter Aperture Spherical radio Telescope (FAST). Because of its high sensitivity and large data rate, FAST requires more accurate and efficient RFI flagging methods than its counterparts. In the last decades, approaches based upon artificial intelligence (AI), such as codes using convolutional neural networks (CNNs), have been proposed to identify RFI more reliably and efficiently. However, RFI flagging of FAST data with such methods has often proved to be erroneous, with further manual inspections required. In addition, network construction as well as preparation of training data sets for effective RFI flagging has imposed significant additional workloads. Therefore, rapid deployment and adjustment of AI approaches for different observations is impractical to implement with existing algorithms. To overcome such problems, we propose a model called RFI-Net. With the input of raw data without any processing, RFI-Net can detect RFI automatically, producing corresponding masks without any alteration of the original data. Experiments with RFI-Net using simulated astronomical data show that our model has outperformed existing methods in terms of both precision and recall. Besides, compared with other models, our method can obtain the same relative accuracy with fewer training data, thus reducing the effort and time required to prepare the training data set. Further, the training process of RFI-Net can be accelerated, with overfittings being minimized, compared with other CNN codes. The performance of RFI-Net has also been evaluated with observing data obtained by FAST and the Bleien Observatory. Our results demonstrate the ability of RFI-Net to accurately identify RFI with fine-grained, high-precision masks that required no further modification.

scholarly journals Car-Following Described by Blending Data-Driven and Analytical Models: A Gaussian Process Regression Approach

2021 ◽  
pp. 036119812110326
Author(s):  
Ignasi Echaniz Soldevila ◽  
Victor L. Knoop ◽  
Serge Hoogendoorn
Keyword(s):  
Gaussian Process Regression ◽  
Large Data ◽  
Driving Behavior ◽  
Large Data Sets ◽  
Training Data ◽  
Data Driven ◽  
Data Sets ◽  
Data Set ◽  
Car Following ◽  
New Variables

Traffic engineers rely on microscopic traffic models to design, plan, and operate a wide range of traffic applications. Recently, large data sets, yet incomplete and from small space regions, are becoming available thanks to technology improvements and governmental efforts. With this study we aim to gain new empirical insights into longitudinal driving behavior and to formulate a model which can benefit from these new challenging data sources. This paper proposes an application of an existing formulation, Gaussian process regression (GPR), to describe individual longitudinal driving behavior of drivers. The method integrates a parametric and a non-parametric mathematical formulation. The model predicts individual driver’s acceleration given a set of variables. It uses the GPR to make predictions when there exists correlation between new input and the training data set. The data-driven model benefits from a large training data set to capture all driver longitudinal behavior, which would be difficult to fit in fixed parametric equation(s). The methodology allows us to train models with new variables without the need of altering the model formulation. And importantly, the model also uses existing traditional parametric car-following models to predict acceleration when no similar situations are found in the training data set. A case study using radar data in an urban environment shows that a hybrid model performs better than parametric model alone and suggests that traffic light status over time influences drivers’ acceleration. This methodology can help engineers to use large data sets and to find new variables to describe traffic behavior.

Sign in / Sign up

Export Citation Format

Share Document