Skip to content

← Lab

Papers & thesis

15 entries — most recent first.

  1. Workshop paper

    A Hackathon for Flood Map Prediction from Geospatial Data with Parsimonious Machine Learning Models

    David Medernach, Cyril Lemaire, Eva Girousse, Julie Keisler, Julie Richon, Nicolas J-B. Brunel

    Tackling Climate Change with Machine Learning — ICLR 2025 Workshop (Climate Change AI), Singapore, April 2025 (non-archival workshop track)

    Flooding poses significant risks across various sectors in France. This paper presents the outcomes of a machine learning hackathon focused on predicting the extent of various types of floods by leveraging a combination of geospatial and climate data. A Convolutional Neural...

    Read →

  2. Preprint DOI

    Intrinsic Properties Ensure Reliable Attractor Dynamics in Learned Neural Assemblies Embedded Within Noisy, Asynchronous Networks

    Matthieu X. B. Sarazin, Jeanne Barthélémy, David Medernach, Jérémie Naudé, Bruno Delord

    bioRxiv (preprint), posted 27 July 2022 (v2). Not peer-reviewed.

    Neural representations rely on the ability of neuronal assemblies to display organized spiking patterns, despite being embedded within noisy networks. These structured patterns arise from attractor dynamics due to activity reverberation promoted by learnt assembly...

    Read →

  3. Journal article DOI

    Online Learning and Memory of Neural Trajectory Replays for Prefrontal Persistent and Dynamic Representations in the Irregular Asynchronous State

    Matthieu X. B. Sarazin, Julie Victor, David Medernach, Jérémie Naudé, Bruno Delord

    Frontiers in Neural Circuits, vol. 15, article 648538

    In the prefrontal cortex (PFC), higher-order cognitive functions and adaptive flexible behaviors rely on continuous dynamical sequences of spiking activity that constitute neural trajectories in the state space of activity. Neural trajectories subserve diverse...

    Read →

  5. Conference paper DOI

    A New Wave: A Dynamic Approach to Genetic Programming

    David Medernach, Jeannie Fitzgerald, R. Muhammad Atif Azad, Conor Ryan

    GECCO '16: Proceedings of the Genetic and Evolutionary Computation Conference, Denver, CO, USA, 20–24 July 2016, pp. 757–764

    Wave is a novel form of semantic genetic programming which operates by optimising the residual errors of a succession of short genetic programming runs, and then producing a cumulative solution. These short genetic programming runs are called periods, and they have...

    Read →

  6. Conference paper DOI

    Evolution of Heterogeneous Cellular Automata in Fluctuating Environments

    David Medernach, Simon Carrignon, René Doursat, Taras Kowaliw, Jeannie Fitzgerald, Conor Ryan

    Proceedings of the Artificial Life Conference 2016 (ALIFE 2016), Chapter 41

    The importance of environmental fluctuations in the evolution of living organisms by natural selection has been widely noted by biologists and linked to many important characteristics of life such as modularity, plasticity, genotype size, mutation rate, learning, or...

    Read →

  7. Book chapter DOI

    Image Classification with Genetic Programming: Building a Stage 1 Computer Aided Detector for Breast Cancer

    Conor Ryan, Jeannie Fitzgerald, Krzysztof Krawiec, David Medernach

    Handbook of Genetic Programming Applications (A. H. Gandomi, A. H. Alavi & C. Ryan, eds.), Chapter 10, pp. 245–287. Springer International Publishing, 2015

    This chapter describes a general approach for image classification using Genetic Programming (GP) and demonstrates this approach through the application of GP to the task of stage 1 cancer detection in digital mammograms. We detail an automated work-flow that begins with...

    Read →

  8. Conference paper DOI

    Evolutionary Progress in Heterogeneous Cellular Automata (HetCA)

    David Medernach, Jeannie Fitzgerald, Simon Carrignon, Conor Ryan

    Proceedings of the European Conference on Artificial Life 2015 (ECAL 2015), pp. 512-519

    Although very controversial in the field of evolutionary biology, the notion of *evolutionary progress* is nevertheless generally accepted in the field of *Artificial Life*. In this article we adopt the definition proposed by Shanahan (2012) to study the existence of...

    Read →

  9. Conference paper DOI

    An Integrated Approach to Stage 1 Breast Cancer Detection

    Jeannie M. Fitzgerald, Conor Ryan, David Medernach, Krzysztof Krawiec

    GECCO '15: Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, Madrid, Spain, 11–15 July 2015, pp. 1199–1206

    We present an automated, end-to-end approach for Stage 1 breast cancer detection. The first phase of our proposed work-flow takes individual digital mammograms as input and outputs several smaller sub-images from which the background has been removed. Next, we extract a set...

    Read →

  10. Conference poster DOI

    Wave: A Genetic Programming Approach to Divide and Conquer

    David Medernach, Jeannie Fitzgerald, R. Muhammad Atif Azad, Conor Ryan

    GECCO Companion '15: Companion of the 2015 Annual Conference on Genetic and Evolutionary Computation, Madrid, Spain, 11–15 July 2015, pp. 1435–1436 (poster / extended abstract)

    This work introduces Wave, a divide and conquer approach to GP whereby a sequence of short, and dependent but potentially heterogeneous GP runs provides a collective solution; the sequence akins wave such that each short GP run is a period of the wave. Heterogeneity across...

    Read →

  11. Conference paper DOI

    Wave: Incremental Erosion of Residual Error

    David Medernach, Jeannie Fitzgerald, R. Muhammad Atif Azad, Conor Ryan

    GECCO Companion '15: Companion of the 2015 Annual Conference on Genetic and Evolutionary Computation, Madrid, Spain, 11–15 July 2015, pp. 1285–1292

    Typically, Genetic Programming (GP) attempts to solve a problem by evolving solutions over a large, and usually pre-determined number of generations. However, overwhelming evidence shows that not only does the rate of performance improvement drop considerably after a few...

    Read →

  12. Conference paper DOI

    Efficient Approaches to Interleaved Sampling of Training Data for Symbolic Regression

    R. Muhammad Atif Azad, David Medernach, Conor Ryan

    2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC), Porto, Portugal, 30 July – 1 August 2014, pp. 176–183. IEEE

    The ability to generalize beyond the training set is paramount for any machine learning algorithm and Genetic Programming (GP) is no exception. This paper investigates a recently proposed technique to improve generalisation in GP, termed Interleaved Sampling where GP...

    Read →

  13. Conference poster DOI

    Efficient Interleaved Sampling of Training Data in Genetic Programming

    R. Muhammad Atif Azad, David Medernach, Conor Ryan

    GECCO Comp '14: Companion of the 2014 Annual Conference on Genetic and Evolutionary Computation, Vancouver, BC, Canada, 12–16 July 2014, pp. 127–128 (poster)

    The ability to generalise beyond the training set is important for Genetic Programming (GP). Interleaved Sampling is a recently proposed approach to improve generalisation in GP. In this technique, GP alternates between using the entire data set and only a single data point....

    Read →

  14. Conference paper DOI

    Building a Stage 1 Computer Aided Detector for Breast Cancer Using Genetic Programming

    Conor Ryan, Krzysztof Krawiec, Una-May O'Reilly, Jeannie Fitzgerald, David Medernach

    Genetic Programming — 17th European Conference, EuroGP 2014, Granada, Spain, 23–25 April 2014. Lecture Notes in Computer Science, vol. 8599, pp. 162–173. Springer

    We describe a fully automated workflow for performing stage1 breast cancer detection with GP as its cornerstone. Mammograms are by far the most widely used method for detecting breast cancer in women, and its use in national screening can have a dramatic impact on early...

    Read →

  15. Conference paper DOI

    Long-Term Evolutionary Dynamics in Heterogeneous Cellular Automata

    David Medernach, Taras Kowaliw, Conor Ryan, René Doursat

    Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation (GECCO '13), Amsterdam, The Netherlands, July 6-10 2013, pp. 231-238

    It is a truism that the complexity of life increases with time, even if the means or measures of it are controversial. Recreating this effectively endless self-generation of new mechanisms and capabilities would be fascinating for its insight into our own origins, and...

    Read →