Hi! I’m a machine learning scientist with a software engineering & mathematics background. Currently putting the finishing touches to a PhD on hyperparameter optimization for deep learning in the Evolutionary Intelligence group at CWI & TU Delft.

I’m excited to apply my expertise to problems that matter, using appropriate tools - which doesn’t always have to mean Generative AI & LLMs :). Still, these technologies are impressive, and my experience with them (generating data, doing RAG, processing text) has been quite positive.

My hobbies include reading (mostly non-fiction and fantasy), hiking, equirhythmic translation, and discussing weird ideas. Always happy to chat about these topics, drop me a line via the header links!

Blog

• Oct 9, 2023

  Transformer explanations: a collection

  Transformer is a powerful architecture that can be difficult to understand. There are many great explanations on the web, each approaching the subject in a different way. Here I link the explanations I liked, and mention who I believe the target audience is for each one.

• Sep 27, 2023

  PBT-NAS: mix architectures during training

  Based on our paper “Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search” (ECAI 2023)

• Aug 25, 2023

  Install nvcc without root

  I needed to install nvcc on our group server, where I lack root privileges. I found a nice guide, in this post I will slightly expand on it by explicitly mentioning every step I had to take.

• Jul 12, 2022

  ENCAS: Search cascades of neural networks in any model pool

  Based on our paper “Evolutionary Neural Cascade Search across Supernetworks” (Best Paper award @ GECCO 2022)

  TL;DR Search for cascades of neural networks in model pools of hundreds of models, optionally using Neural Architecture Search to efficiently generate many diverse task-specific neural networks. Get dominating trade-off fronts on ImageNet and CIFAR-10/100, improved ImageNet SOTA (of publicly available models).

• Jan 15, 2017

  Document recognition with Python, OpenCV and Tesseract

  Recently I’ve conducted my own little experiment with the document recognition technology: I’ve successfully went from an image to the recognized editable text.

subscribe via RSS