← Back to the training program

Ricardo Guerrero


Jose Alberto Arcos Sánchez


Classification, Detection, Segmentation and something more: Computer Vision and Deep Learning with code

Artificial Intelligence - Deep learning, Machine Learning



This course will be divided into 4 modules. You’ll be trained how to:

·Image Classification, Object Detection, Segmentation and the Bonus Track. The goal of this course is to teach the attendants the tools, the know-how and the way to tackle end-2-end the most extended Computer Vision tasks.

·Developing in-house code is usefull, but sometimes there is a 3rd party service that solves our problem for us with a reasonable cost. We will review the tools at our hands and learn when to code and when to lean on an external API. Coding is beautiful, but a short time-to-market is also important.

·Are you familiar with the expression "a monkey with a crossbow"? Machine Learning and specially Deep Learning can trick us returning beautiful metrics... but a deeper understanding of the underlying process is needed to hunt the trickiest bugs. We will learn how to set them under control.


·Just some Python knowledge and a Gmail account for using Google Colab.
·A laptop able to run docker containers will be required.

Nature of the training

Dogs, cats, flowers... the true beauty of computer vision is that this field is really pleasant to transmit. With just a couple of pictures I can explain advanced concepts even to my grandmother: this rectangle? Yes, my program says that there is a cat inside. No need to read giant logs or interpret equations to understand the business.

There are three main tasks in computer vision: Image Classification (aka Labelling), Object Detection and Semantic Segmentation. Dominating these will allow you to deal with the most of computer vision problems you will face. This full-day course will show you how to tackle them with Python and Keras.

And there will be a bonus module covering a very helpful topic nowadays. Do you want to know what is it?


Big Data Spain will issue the certificate for this course to prove subject matter competency


Developers with some Machine Learning interesting or Data Scientist who wants to learn Deep Learning and Computer Vision

Bio of the instructor - Ricardo Guerrero

Ricardo Guerrero is a Telecommunication Engineer by the Universidad de Alcalá with a huge passion for Computer Vision, Machine Learning and Self-Driving Cars.

He joined the Research Lab team in BBVA Next Technologies (previously known as BEEVA) more than 2 years ago. GPUs, Computer Vision and Deep Learning where his focus. Now, as one of the leaders of the Data Lab department takes care of the internal community, trainings and best practices while fighting fraud in banking using cutting-edge Cloud Computing architectures, XGBoost and PyTorch.

Bio of the instructor - Jose Alberto Arcos Sánchez

Jose Alberto is a very geek Industrial Engineer with focus on Data Analytics with R and Python.

Since his arrival to BBVA Next Technologies has been specialized in Time Series and Model Interpretability. As one of the leaders of the Data Lab department takes care of commercial opportunities and technological strategy.