As a machine learning engineer, I am passionate about meta-learning, particularly in combining it with visual self-supervised learning. I am interested in developing intelligent agents that can rapidly acquire new skills and adapt to novel environments with minimal supervision.
Research
Regularized Meta-Learning for Neural Architecture Search
Rob van Gastel, Joaquin Vanschoren
AutoML-Conf Late-Breaking Workshop 2022
paper / code
We apply regularization techniques to the inner-loop neural architecture search to improve meta-learning, adapting to new tasks more quickly.
Projects
Finetuning Transferable Vision Transformer Weights
Finetuning the encoder weights of the self-supervised learning method DINOv2 using a simple 1x1 convolution encoder and Low-Rank Adaptation (LoRA) allows for adaptation to the Pascal VOC and ADE20k datasets within a few epochs.
Meta-Reinforcement Learning Algorithms
Implementations of Meta-Reinforcement Learning algorithms designed to quickly adapt policies to new, related tasks within a few episodes.
Discrete Soft Actor-Critic with Memory-Based Networks
Implemented the discrete Soft-Actor Critic (SAC) algorithm with RNN-conditioned policy and value functions. This conditioning is used to address challenges in partially observable environments.
A native iOS interval timer app to help people time their workouts in collaboration with Max Wammes and Mehmet Bakirci.