All you need to know about this library for scalable hyperparameter tuning of machine learning models — The optimization of model hyperparameters (or model settings) is perhaps the most important step in training a machine learning algorithm as it leads to finding the optimal parameters that minimize your model’s loss function. This step is also essential to building generalizable models that are not prone to overfitting.

How to use BigQuery in data management, data exploration, and visualization — BigQuery is one of the current cloud data warehouses in the market. This tool is unique in how low-maintenace it is. Additionally, the architecture of BigQuery — which is known as server-less infrastructure — allows users to focus more on the analysis of their data. The data stored in BigQuery…

An overview of the different roles that you can pursue and how to be good in this competitive field — During the last couple of years, the demand for data scientists has been growing. Many companies look for experienced people who can give value to the large amounts of data currently available. For many students, especially those finishing a Ph.D. in natural sciences, becoming a data scientist is a good…

Using a mixture of Bayes optimization and linear regression to fit one of the most common functions in physics. — By: Carmen Martínez-Barbosa and José Celis-Gil A couple of days ago one of our colleagues asked us how to fit the data from a harmonic signal with a reasonable knowledge of its behavior. This seems a standard problem as in physics many processes are periodic. The piston of a motor…

Logistical hubs play a critical role in the national and regional infrastructure, and in economic development. They can bring foreign investment, tourism, trade, employment — also referred to as “positive externalities.” In Europe, one of the most important logistical hubs are airports. According to recent studies, European airports contribute to…