María Pérez-Ortiz

Research Associate in Computer Science
Computer Laboratory, University of Cambridge

Image
Images processed by Deep dream generator.

About Me

I'm Maria, welcome to my website :). At the moment, I'm a postdoctoral research associate at the Computer Laboratory in the University of Cambridge, very happily enjoying the British weather and doing research on the intersection of machine learning, computer graphics and psychophysics, under the supervision of Dr Rafal Mantiuk in the Rainbow group. I hold a Bachelor degree in Computer Science (2011), a Master degree in Intelligent Systems (2012) and a PhD in Machine Learning (2015).

In my research I have mostly worked towards the development of new machine learning methods, focusing on ordinal classification, support vector machines and imbalanced datasets. But I have also been always eager about applying these techniques to different fields: I have worked with a liver transplantation team to create a machine learning model for organ allocation (which is being tested in several hospitals in Spain now, to be used as decision support system), I have contributions in the field of climate dynamics using time series analysis (because of a project performed with a team of the European Spacial Agency), I have worked in an agricultural research institute for creating a model to detect weeds using drones and image analysis and, most recently, I have collaborated on a project to create a machine learning based model to detect cancer skin and predict its stage. At the moment, I’m working on a project using psychophysics and machine learning to better understand human visual perception, a project in collaboration with Apple and the University of Liverpool.

My current interests can be summarised in: The future of machine learning and its impact on our society (changing job market, positive computing), the analysis of non standard data (such as image, speech or text mining), how to transfer expert knowledge to AI and virtually any topic slightly related to AI (Computer vision? I'm in! Natural language processing? Hell yeah! Bioinformatics? Yes please! Robotics? Whoa!). A few curiosities: I also hold a Master degree in Health Coaching, I have been dancing since I was 3 years old (ballet, flamenco, you name it!), I'm an avid reader (now very into audiobooks) and I believe my learning rate is quite high (went from an English A2 to a C2 level in 3 years and presented my PhD at the age of 24), but my forgetting rate is also extremely high (a defense mechanism not to overfit). Also, I'm social event organiser at Women@CL.

My CV Publications Google Scholar ResearchGate

My Skills

Machine learning 81%
Image processing (still learning!) 59%
Sarcasm and the art of procastination 97%

Experience

Research

I joined a research group and started doing research when I was 20 years old. Since then I have collaborated with different institutions in more than 7 research projects and I have received 6 awards for my research.

Teaching

I have collaborated in different courses on machine learning, scientific programming and business statistics (either lecturing or preparing materials) and guided a few final degree projects.

Coding

Most of the code that I have developed is available online. One of the biggest code projects in which I have been involved is a machine learning framework in Matlab for ordinal regression (ORCA, which was initially part of my final BSc project degree but has been extended afterwards).

Writing

I enjoy writing very much. I have written/collaborated in more than 60 scientific papers (journal and conferences). I also write some non-scientific things in my spare time. However, I have no idea whatsoever of how to use either Word or Powerpoint, LaTeX and beamer rules!

Education

  • B.Sc in Computer Science, University of Córdoba (Spain). Collaborator student in the Dpt. of Computer Science and Numerical Analysis.
  • M.Sc in Intelligent Systems, University of Córdoba (Spain). Honorary student of the Dpt. of Computer Science and Numerical Analysis.
  • Ph.D in Computer Science, University of Córdoba (Spain), Cum Laude. International Doctor Mention. Thesis available here.

Research experience

  • Associate researcher (06/2017-now), Rainbow group, Computer Laboratory, University of Cambridge (UK). Research: machine learning, computer vision, psychophysics, visual perception. Working under the supervision of Dr Rafal Mantiuk.
  • Visiting academic (02/2017-05/2017), School of Computer Science, University of Birmingham (UK). Research: imbalanced data and semi-supervised learning. Working under the supervision of Prof. Peter Tino.
  • Lecturer/associate researcher (09/2015-05/2017), Dpt. of Quantitative Methods, University Loyola Andalucía (Spain). Research: imbalanced data, time-series analysis, semi-supervised learning.
  • Research assistant (03/2014-08/2015), imaPing group, Institute for Sustainable Agriculture (Spanish National Research Council). Research: image analysis, computer vision, applications of machine learning in agriculture. Working under the supervision of Dr. Francisca López-Granados.
  • Visiting academic (01/2014-02/2014), Centro Singular de Investigación en Tecnologías de la Información (CITIUS), University of Santiago de Compostela (Spain). Research: ordinal classification. Collaboration with Dr. Manuel Fernández Delgado and Dr. Alberto Bugarín.
  • Visiting academic (05/2013-07/2013), School of Computer Science, University of Birmingham (UK). Research: imbalanced data and kernel algorithms. Collaboration with Prof. Peter Tino and Prof. Xin Yao.
  • Research assistant/teaching assistant (02/2012-02/2014), AYRNA group, Dpt. of Computer Science and Numerical Analysis, University of Córdoba (Spain). Research: ordinal classification and data, kernel learning. Working under the supervision of Prof. César Hervás-Martínez.
  • Research assistant (06/2011-12/2011), AYRNA group, Dpt. of Computer Science and Numerical Analysis, University of Córdoba and ASTELLAS Pharma (Spain). Research: multiclass classification, application of machine learning for biomedicine, donor-recipient allocation. Working under the supervision of Prof. César Hervás-Martínez.

Research awards

  • Córdoba Young Awards: University and Innovation, 2017, Regional Government of Andalusia. Learn more here.
  • Young researchers in Computer Science, 2017, BBVA and the Spanish Scientific Society for Computer Science, 5000€. Learn more here.
  • Research annual award (recognition for my research at the university), 2017, University Loyola Andalucía.
  • First honorary award: PhD program of Engineering and Technology, 2016, University of Córdoba.
  • Second award: Women in artificial intelligence, 2015, Spanish Association for Artificial Intelligence, 150€.
  • Third award and award of the public: Your thesis in three minutes, 2013, Spanish Network for the Advance and Transfer of Applied Computational Intelligence, 1500€. Learn more here.

My research

  • Theoretical ML: Find below a summary of the research topics in which I have been working up to this date. Mostly, these comprise: Ordinal classification or regression (classifiers in which the labels follow a given order), learning kernel functions (for kernel classifiers, such as Support Vector Machines), imbalanced data (and more specifically how to create synthetic data to oversample the minority class), weakly supervised problems (e.g. semi-supervised learning) and image and time-series analysis.

  • Summary of my research topics

  • Applied ML: I have worked with a liver transplantation team to create a ML model for organ allocation (which is being tested in several hospitals in Spain now, to be used as decision support system), I have collaborated in a project with a team of the European Spacial Agency to model paleoclimate dynamics using time series analysis, I have worked in an agricultural research institute for creating a model to detect weeds using drones and image analysis, I have performed a study of the most influcential factors for happiness using ML, I have studied also the use of ML to predict the production of renewable energies, and, most recently, I have worked with some colleagues on a project to create a ML based model to detect cancer skin and predict its stage. At the moment, I’m working on a project using psychophysics and ML to better understand human visual perception and image quality. Real-world data, yay!

Press coverage

My collaborators up to now

Latest works and posts

Latest things that I have been working on, some of my writing and super exciting news!

Latest Products Image

Reading group on machine learning for imaging Research

I have started a reading group on machine learning for imaging at the Computer Lab. Join us!

Read More

The "adas" (generations of women who have followed Ada Byron in her desire of breaking the mold, of creating and programming), prefer the structure "switch...case" over the structure "if...else", given its infinite possibilities. Programming the world for the “adas” implies creating the conditions for each one to be whatever one wants to be, even when this corresponds to something not referenced yet with a word in the world, or when it can not be imagined clearly; it implies creating the conditions that even allow us to change our mind.

Top