Manuel Gijón Agudo

Data Scientist and Developer

Mathematician by the Autonomous University of Madrid, and master's degree in Advanced Mathematics and Mathematical Engineering by the Polytechnic University of Catalonia.

Passionate about technology

Lifelong learner


Machine Learning Engineer and Full Stack Developer


  • Develop of products for internal use from scratch for data collecting, maintenance and cleaning.
  • Implementation of Machine Learning and Deep Learning algorithms for classification and prediction.
  • Dev/ops, maintenance and continuous integration of the created platforms.
  • TECH STACK (Artificial Intelligence): Python (Numpy, Pandas, Matplotlib, Seaborn and Bokeh for data visualization, Scikit-learn for Machine Learning models and TensorFlow and Keras for Deep Learning implementations).
  • TECH STACK (Full Stack):Django (Python framework for backend development), HTML5, CSS, JavaScript (vanilla and ThreeJS).
  • TECH STACK (Dev/Ops)Docker and Jenkins.

Oct 2019 - Jun 2020

Project Manager

CARNET Future Mobility Research Hub

  • Maintain the company’s main website.
  • Create, upload and update web pages for different projects (Autonomous Driving Challenge 2018, Citython 2018, Symposium 2018).
  • Layout and disseminate newsletters through the platform MailChimp.
  • Participate in the organization and development of the event Citython 2018 (a Hackathon focused on the development of products and services related to the concept ’Smart Cities’).
  • TECH STACK: HTML5, CSS, JavaScript.

May 2018 - Nov 2018


Analyzing Distances in Word Embeddings and Their Relation with Seme Analysis

IOSPRESS, Artificial Intelligence Research and Development
Authors: Manuel Gijón Agudo, Armand Vilalta Arias (HPAI, BSC) and Dario Garcia-Gasulla (HPAI, BSC).

Abstract: Word embeddings have recently become a fundamental tool of Natural Language Processing, with application to tasks like machine translation or image annotation. The high-dimensional space defined by these embeddings is typically explored and exploited through distance-based operations. In this paper we work on the problem of finding words related between them in a text embedding. This relationship can be of different kind, we focus in semantic relations like synonymy and antonym. We explore the idea of using the distance between norms instead of, like other authors has done before, the vector that units them. We present different norms, some of them well known in the literature and others no so widely used and also we introduce a new one and its theoretical mathematical framework. We also give an explanation of why them work properly or not and compare their performance on the two most used embeddings, GloVe and Word2Vec.

22 Congrés Internacional de l’Associació Catalana d’Intel·ligncia Artificial (Mallorca, Balearic Islands).
Link to the paper.
October 2019


Universitat Politècnica de Catalunya (UPC)

Master's degree in Advanced Mathematics and Mathematical Engineering (MAMME)

Relevant Coursework: Codes and Cryptography, Discrete and Algorithmic Geometry, Graph Theory, Estadística para la Gestión Empresarial (from MESIO, Máster universitario en Estadística e Investigación Operativa).

2012 - 2017

Universidad Autónoma de Madrid (UAM)

Bachelor in Mathematics
2012 - 2017

2015-2016: Universitat Autònoma de Barcelona (UAB).

2016-2017: Universitat Politècnica de Catalunya (UPC).

Complementary education (selected)

Deep Learning Coursera Specialization

  • Neural Networks and Deep Learning.
  • Improving Deep Neural Networks: Hyperparameter tuning Regularization and Optimization.
  • Structuring Machine Learning Projects.
  • Convolutional Neural Networks.
  • Sequence Models.

Artificial Intelligence

  • Machine Learning. Stanford University, Coursera.
  • Machine Learning Aplicado con Python. Platzi.

Software Development

  • Curso Básico de Jenkins. Platzi.
  • Fundamentos de Docker. Platzi.
  • Curso de Docker. Platzi.
  • Fundamentos de JavaScript. Platzi.
  • Introducción a Terminal y Línea de Comandos. Platzi.


Programming Languages & Tools
  • Data Science: Python (Numpy, Pandas, Sklearn, Scikit, Pyplot, Seaborn, Bokeh, ...) and R. During my accademic years I studied SAS too.
  • Web development: I have experience with Django for the as framework for the backend and HTML5, CSS and JavaScipt for the frontend.
  • I have experience using Docker (in fact, I've been using in all my projects since I discovered it) and Jenkins for continuous integration.
  • In the past, I used C, C++, Java and Matlab.
  • Experience with Git systems (mostly with Github) and currently in love with Unix systems.


Apart from discovering new technologies, I play guitar almost every day and do Brazilian Jiu-Jitsu as much as I can.

Also, I spend part of my free time learning new mathematical concepts, trying new programming languages and reading, programming and implementing Artificial Intelligence algorithms.