Due to developments in electronic medical records and medical imaging technology, the healthcare industry has witnessed a significant increase in the volume of medical data [1, 2]. This enormous growth in medical data has made it a great tool for enhancing medical diagnosis and therapy. Unfortunately, healthcare practitioners frequently confront difficulties in evaluating and utilizing this huge amount of data effectively. In potential lead exposure at the zip code level is predicted using machine learning on patients' Blood Lead Levels (BLL) dataset. Machine learning provides a way to automate the interpretation and analysis of medical data, including medical images, by recognizing patterns within the information [3].

Automated machine learning (AutoML) algorithms have grown in popularity due to their high performance and flexibility to adapt to different problems and data sets. With the increasing number of AutoML algorithms, deciding which would best suit a given problem becomes increasingly more work. Therefore, it is essential to use complex and challenging benchmarks which would be able to differentiate the AutoML algorithms from each other. This paper compares the performance of four different AutoML algorithms: Tree-based Pipeline Optimization Tool (TPOT), Auto-Sklearn, Auto-Sklearn 2, and H2O AutoML. We use the Diverse and Generative ML benchmark (DIGEN), a diverse set of synthetic datasets derived from generative functions designed to highlight the strengths and weaknesses of the performance of common machine learning algorithms. We confirm that AutoML can identify pipelines that perform well on all included datasets. Most AutoML algorithms performed similarly; however, there were some differences depending on the specific dataset and metric used.

Lunit is an AI software company devoted to developing advanced medical image analytics and data-driven imaging biomarkers via cutting-edge deep learning technology. AutoML team develops a cloud-based AutoML platform and AutoML algorithms that run on the platform. Our team already has built a cloud-based hyperparameter tuning platform and achieved significant performance improvements in the real-world products with the power of AutoML. Recently, we are focusing on improving the AutoML algorithm to further boost the performance of various AI models in Lunit. We are looking for a research scientist with a strong motivation to achieve meaningful improvements in real-world scenarios.

In this post, we would like to discuss such a well-known and extensively described topic as preprocessing tabular data in data science. You may ask, "Why do we need it? There is nothing new to say!" Indeed, what could be more trivial than tabular data processing for machine learning models? But we'll try to collect as much information as possible into one ultimate guide and give it through the perspective of automatic machine learning (AutoML). Disclaimer: all the approaches we describe below are not the only ones. We have used them during the development of our open-source AutoML framework FEDOT. This project has its own specifics in both architecture and development design approaches.

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their great success, the selection of suitable compression methods and design of details of the compression scheme are difficult, requiring lots of domain knowledge as support, which is not friendly to non-expert users. To make more users easily access to the model compression scheme that best meet their needs, in this paper, we propose AutoMC, an effective automatic tool for model compression. AutoMC builds the domain knowledge on model compression to deeply understand the characteristics and advantages of each compression method under different settings. In addition, it presents a progressive search strategy to efficiently explore pareto optimal compression scheme according to the learned prior knowledge combined with the historical evaluation information. Extensive experimental results show that AutoMC can provide satisfying compression schemes within short time, demonstrating the effectiveness of AutoMC.

The pipeline optimization problem in machine learning requires simultaneous optimization of pipeline structures and parameter adaptation of their elements. Having an elegant way to express these structures can help lessen the complexity in the management and analysis of their performances together with the different choices of optimization strategies. With these issues in mind, we created the AutoMLPipeline (AMLP) toolkit which facilitates the creation and evaluation of complex machine learning pipeline structures using simple expressions. We use AMLP to find optimal pipeline signatures, datamine them, and use these datamined features to speed-up learning and prediction. We formulated a two-stage pipeline optimization with surrogate modeling in AMLP which outperforms other AutoML approaches with a 4-hour time budget in less than 5 minutes of AMLP computation time.