Hi there! 👋


I am a final-year PhD researcher in Computational Neuroscience working under the umbrella of Marie-Curie Actions (MSCA-ITN). I'm focused on leveraging Machine Learning as a method for developing better tools for Neuroscience research and as a model for studying the human brain.

By building on state-of-the-art active sampling and representation learning research we are developing human-in-the-loop frameworks to optimize brain signal and creating novel AutoML frameworks that benefit from small datasets. I’m also looking into using auto-regressive models to build normative models of the human brain.

Download my CV.


Education

  • PhD in Computational Neuroscience, 2022

    Birkbeck College London

  • MSc Thesis - Visiting Student, 2018

    Imperial College London

  • MSc in Biomedical Engineering, 2018

    Instituto Superior Tecnico

Achievements
  • PAC2019 Brain age competition - Top10
  • King’s College Neuroimaging Hackathon - 1st Place (2019)
  • Roller-hockey National University League - 1st Place (2015)

Skills

python
Python
pytorch
PyTorch
tensorflow
Tensorflow
Unity
AutoML
Generative Models

Projects

*
All Deep Learning Classical ML Software Development
Building new methods with Bayesian Optimization

Building new methods with Bayesian Optimization

Exploring Bayesian Optimization as a tool for exploitation of configurational spaces in Neuroscience

Video Paper 1 Code
Normative Modelling in Psychiatry

Normative Modelling in Psychiatry

Using Auto-regressive models to identify out-of-distribution brain data to identify disorders

Paper 1 Code
Relevance Vector Machine

Relevance Vector Machine

A scikit-learn style implementation of Tippings’s RVM algorithm.

Install Code
Brain-Age Problem

Brain-Age Problem

Deploying classical ML models for very-high-dimensional data. Top-10 on PAC2019 competition.

Paper 1 Paper 2
Generative Art

Generative Art

I like to take generative models and try to build creative things with it.

Modelling Behaviour

Modelling Behaviour

Using neural networks to simulate human performance and interpret the model’s trained weights

Thesis Paper 1 Code

Recent Publications

Lea Baecker, Jessica Dafflon, Pedro F. da Costa, Rafael Garcia-Dias, Sandra Vieira, Cristina Scarpazza, Vince D. Calhoun, João R. Sato, Andrea Mechelli, Walter H.L. Pinaya (2021). Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data. Hum. Brain Mapp..

Cite Code DOI

Federico E. Turkheimer, Erik D. Fagerholm, Miriam Vignando, Jessica Dafflon, Pedro F. da Costa, Paola Dazzan, Robert Leech (2020). A GABA Interneuron Deficit Model of the Art of Vincent van Gogh. Front. Psychiatry.

Cite DOI

P. da Costa, R. Lorenz, R. Monti, E. Jones, R. Leech (2020). Bayesian Optimization for real-time, automatic design of face stimuli in human-centred research. ICML2020 - WS AutoML.

PDF Cite Code

Pedro F. da Costa, Jessica Dafflon, Walter H. L. Pinaya (2020). Brain-Age Prediction Using Shallow Machine Learning: Predictive Analytics Competition 2019. Frontiers in Psychiatry.

PDF Cite Code DOI

Jessica Dafflon, Pedro F. da Costa, František Váša, Ricardo Pio Monti, Danilo Bzdok, Peter J. Hellyer, Federico Turkheimer, Jonathan Smallwood, Emily Jones, Robert Leech (2020). Neuroimaging: Into the multiverse. bioRxiv.

Cite DOI

See all publications

Posts

Modelling Coloured Images
Autoregressive Models — PixelCNN

Word Cloud

Alzheimer’s disease anomaly detection Auto-regressive models autoencoders Autoregressive Bayesian Optimization Brain-age Cognitive Processes Deep Learning generative models LSTMs Machine Learning Modelling behaviour Neuroscience Normative modelling PixelCNN Regression Analysis Relevance Vector Machine RNNs Software Development

Contact

Generative art

Some examples

Generative art

Some examples

Generative art

Some examples

Previous Next