Compressing Prime Numbers: Kolmogorov Complexity 101
A tiny bit of light on Kolmogorov Complexity and the incompressibility method.
Welcome to my site! I am a computer scientist and student from the gorgeous and oxygen-deprived city of Quito, Ecuador. Currently, I am a PhD candidate in Computer Science at the University of Cambridge, where I have the extreme luck to be supervised by Mateja Jamnik and to be supported by a Gates Cambridge scholarship. As part of my research, I am interested in broadening the applications of artificial intelligence in healthcare by making learning algorithms more interpretable. Specifically, I am interested in concept-based interpretability and its wider applications to deep learning within medical domains. If you would like to read more about this, please take a look at my research page. Whenever I am not breaking things at my daily job and research, I enjoy needlessly hoarding weird book editions, casually attempting to play pickup football, and opening way too many articles in my browser thinking I'll be able to read them all.
In this site I'll be collecting my personal thoughts on what I am sure will be a seemingly random selection of topics. If you want to know more about my research or myself, feel free to shoot me an email with any questions and/or good jokes you may have. In the meantime, I hope you find some of the posts in this site both slightly entertaining and interesting for you!
Recent News
| [October 2024] | Our work on unsupervised bias mitigation was accepted at ECCV 2024 as an oral and nominated as Best Paper (within the top 15 papers)! |
| [August 2024] | Our workshop on Human-Interpretable AI was accepted at KDD 2024. |
| [July 2024] | One paper accepted at ICML 2024 where I will also be a co-organizer of the LatinX in AI (LXAI) Affinity Workshop. |
| [January 2024] | Joined The Alan Turing Institute as a PhD enrichment student. |
| [October 2023] | Joined Sony AI's AI Ethics team as a research intern. |
| [September 2023] | Our Intervention-aware Concept Embedding Model (IntCEM) paper was accepted at NeurIPS 2023 as a spotlight (top ~3.06% of papers)! |
| [July 2023] | Our Tabular Concept Bottleneck Model (TabCBM) paper was accepted at Transactions of Machine Learning Research (TMLR) and at ICML's 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH) |
| [April 2023] | Our Deep Concept Reasoner (DCR) paper was accepted at ICML 2023 and at ICML's Differentiable Almost Everything Workshop! |
| [March 2023] | Our paper on the effect of uncertainty for concept interventions was accepted at the AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2023! |
| [November 2022] | Our paper on metrics for measuring concept quality and leakage was accepted at AAAI 2023 as a spotlight presentation! |
| [September 2022] | Our Concept Embedding Model (CEM) paper was accepted at NeurIPS 2022! |
| [December 2021] | My MPhil thesis work was accepted at NeurIPS's Workshop on eXplainable AI approaches for debugging and diagnosis (XAI4Debugging@NeurIPS) as a spotlight presentation! |
| [June 2021] | Awarded Gates Cambridge scholarship to study for a Computer Science PhD under the supervision of Professor Mateja Jamnik. |
Recent Posts
On Bizarre Mathematics
Welcome to my blog! Here is something weird for you…