A machine learning solver for high-dimensional integrals: Solving Kolmogorov PDEs by stochastic weighted minimization and stochastic gradient descent through a high-order weak approximation scheme of SDEs with Malliavin weights

The satisfaction of employees is very important for any organization to make sufficient progress in production and to achieve its goals. Organizations try to keep their employees satisfied by making their policies according to employees’ demands which help to create a good environment for the collective. For this reason, it is beneficial for organizations to perform staff satisfaction surveys to be analyzed, allowing them to gauge the levels of satisfaction among employees. Sentiment analysis is an approach that can assist in this regard as it categorizes sentiments of reviews into positive and negative results. In this study, we perform experiments for the world’s big six companies and classify their employees’ reviews based on their sentiments. For this, we proposed an approach using lexicon-based and machine learning based techniques. Firstly, we extracted the sentiments of employees from text reviews and labeled the dataset as positive and negative using TextBlob. Then we proposed a hybrid/voting model named Regression Vector-Stochastic Gradient Descent Classifier (RV-SGDC) for sentiment classification. RV-SGDC is a combination of logistic regression, support vector machines, and stochastic gradient descent. We combined these models under a majority voting criteria. We also used other machine learning models in the performance comparison of RV-SGDC. Further, three feature extraction techniques: term frequency-inverse document frequency (TF-IDF), bag of words, and global vectors are used to train learning models. We evaluated the performance of all models in terms of accuracy, precision, recall, and F1 score. The results revealed that RV-SGDC outperforms with a 0.97 accuracy score using the TF-IDF feature due to its hybrid architecture.

Download Full-text

APPLICATION OF MACHINE LEARNING ALGORITHMS FOR PROCESSING COMMENTS FROM THE YOUTUBE VIDEO HOSTING UNDER TRAINING VIDEOS

Science and Transport Progress Bulletin of Dnipropetrovsk National University of Railway Transport ◽

10.15802/stp2020/225264 ◽

2021 ◽

pp. 33-42

Author(s):

L. S. Koriashkina ◽

H. V. Symonets

Keyword(s):

Machine Learning ◽

Gradient Descent ◽

Russian Language ◽

Stochastic Gradient ◽

Machine Learning Algorithms ◽

Stochastic Gradient Descent ◽

Support Vector ◽

Learning Methods ◽

Machine Learning Methods ◽

Gradient Enhancement

Purpose. Detecting toxic comments on YouTube video hosting under training videos by classifying unstructured text using a combination of machine learning methods. Methodology. To work with the specified type of data, machine learning methods were used for cleaning, normalizing, and presenting textual data in a form acceptable for processing on a computer. Directly to classify comments as “toxic”, we used a logistic regression classifier, a linear support vector classification method without and with a learning method – stochastic gradient descent, a random forest classifier and a gradient enhancement classifier. In order to assess the work of the classifiers, the methods of calculating the matrix of errors, accuracy, completeness and F-measure were used. For a more generalized assessment, a cross-validation method was used. Python programming language. Findings. Based on the assessment indicators, the most optimal methods were selected – support vector machine (Linear SVM), without and with the training method using stochastic gradient descent. The described technologies can be used to analyze the textual comments under any training videos to detect toxic reviews. Also, the approach can be useful for identifying unwanted or even aggressive information on social networks or services where reviews are provided. Originality. It consists in a combination of methods for preprocessing a specific type of text, taking into account such features as the possibility of having a timecode, emoji, links, and the like, as well as in the adaptation of classification methods of machine learning for the analysis of Russian-language comments. Practical value. It is about optimizing (simplification) the comment analysis process. The need for this processing is due to the growing volumes of text data, especially in the field of education through quarantine conditions and the transition to distance learning. The volume of educational Internet content already needs to automate the processing and analysis of feedback, over time this need will only grow.

Download Full-text

Parallel multiclass stochastic gradient descent algorithms for classifying million images with very-high-dimensional signatures into thousands classes

Vietnam Journal of Computer Science ◽

10.1007/s40595-013-0013-2 ◽

2014 ◽

Vol 1 (2) ◽

pp. 107-115 ◽

Cited By ~ 12

Author(s):

Thanh-Nghi Do

Keyword(s):

Gradient Descent ◽

Stochastic Gradient ◽

Stochastic Gradient Descent ◽

High Dimensional ◽

Descent Algorithms ◽

Very High

Download Full-text

BROCCOLI: overlapping and outlier-robust biclustering through proximal stochastic gradient descent

Data Mining and Knowledge Discovery ◽

10.1007/s10618-021-00787-z ◽

2021 ◽

Author(s):

Sibylle Hess ◽

Gianvito Pio ◽

Michiel Hochstenbach ◽

Michelangelo Ceci

Keyword(s):

Data Mining ◽

Matrix Factorization ◽

Gradient Descent ◽

Stochastic Gradient ◽

Stochastic Gradient Descent ◽

High Dimensional ◽

Optimization Scheme ◽

Real World Data ◽

Binary Constraints ◽

Selection Of

AbstractMatrix tri-factorization subject to binary constraints is a versatile and powerful framework for the simultaneous clustering of observations and features, also known as biclustering. Applications for biclustering encompass the clustering of high-dimensional data and explorative data mining, where the selection of the most important features is relevant. Unfortunately, due to the lack of suitable methods for the optimization subject to binary constraints, the powerful framework of biclustering is typically constrained to clusterings which partition the set of observations or features. As a result, overlap between clusters cannot be modelled and every item, even outliers in the data, have to be assigned to exactly one cluster. In this paper we propose Broccoli, an optimization scheme for matrix factorization subject to binary constraints, which is based on the theoretically well-founded optimization scheme of proximal stochastic gradient descent. Thereby, we do not impose any restrictions on the obtained clusters. Our experimental evaluation, performed on both synthetic and real-world data, and against 6 competitor algorithms, show reliable and competitive performance, even in presence of a high amount of noise in the data. Moreover, a qualitative analysis of the identified clusters shows that Broccoli may provide meaningful and interpretable clustering structures.

Download Full-text