Deep learning (DL) techniques have obtained remarkable achievements on various tasks, such as image recognition, object detection, and language modeling. However, building a high-quality DL system for a specific task highly relies on human expertise, hindering its wide application. Meanwhile, automated machine learning (AutoML) is a promising solution for building a DL system without human assistance and is being extensively studied. This paper presents a comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML. According to the DL pipeline, we introduce AutoML methods – covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS) – with a particular focus on NAS, as it is currently a hot sub-topic of AutoML. We summarize the representative NAS algorithms’ performance on the CIFAR-10 and ImageNet datasets and further discuss the following subjects of NAS methods: one/two-stage NAS, one-shot NAS, joint hyperparameter and architecture optimization, and resource-aware NAS. Finally, we discuss some open problems related to the existing AutoML methods for future research.

AutoML: A survey of the state-of-the-art

TELKOMNIKA : Telecommunication, Computing, Electronics and Control

Advancements in information technology is contributing to the excessive rate of big data generation recently. Big data refers to datasets that are huge in volume and consumes much time and space to process and transmit using the available resources. Big data also covers data with unstructured and structured formats. Many agencies are currently subscribing to research on big data analytics owing to the failure of the existing data processing techniques to handle the rate at which big data is generated. This paper presents an efficient classification and reduction technique for big data based on parallel generalized Hebbian algorithm (GHA) which is one of the commonly used principal component analysis (PCA) neural network (NN) learning algorithms. The new method proposed in this study was compared to the existing methods to demonstrate its capabilities in reducing the dimensionality of big data. The proposed method in this paper is implemented using Spark Radoop platform.

An effective classification approach for big data with parallel generalized Hebbian algorithm

– Technologies of marketing evolve over time. This phenomenon is due to the need to ensure the concept of marginal utility, called the mainstream, and the possible leveling of market failures in the classical sense. The development of the theoretical sections of the economy allows us to form a model of paradigm in thinking of the society. The complex of measures for the promotion of goods is transformed into a universal mechanism of the market, which forms consumer preferences, volume of consumer choice and supply chain, which is reflected in this research. The influence of behavioral Economic development in the key of innovative marketing technologies is also considered.

https://ojs.excelingtech.co.uk/index.php/IJSCM/article/download/2394/1262

The Effect of Supply Chain and Consumer Preferences on the Formation of Economic Model

Railroad accident analysis using extreme gradient boosting.

Recently Big Data has become one of the important new factors in the business field. This needs to have strategies to manage large volumes of structured, unstructured and semi-structured data. It’s challenging to analyze such large scale of data to extract data meaning and handling uncertain outcomes. Almost all big data sets are dirty, i.e. the set may contain inaccuracies, missing data, miscoding and other issues that influence the strength of big data analytics. One of the biggest challenges in big data analytics is to discover and repair dirty data; failure to do this can lead to inaccurate analytics and unpredictable conclusions. Data cleaning is an essential part of managing and analyzing data. In this survey paper, data quality troubles which may occur in big data processing to understand clearly why an organization requires data cleaning are examined, followed by data quality criteria (dimensions used to indicate data quality). Then, cleaning tools available in market are summarized. Also challenges faced in cleaning big data due to nature of data are discussed. Machine learning algorithms can be used to analyze data and make predictions and finally clean data automatically.

/pdf/a-survey-on-cleaning-dirty-data-using-machine-learning-3pusi8fl4e.pdf

Jesmeen M. Z. H

Papers

A Survey on Cleaning Dirty Data Using Machine Learning Paradigm for Big Data Analytics