A Little About Me
My name is Igor Lima Rocha Azevedo. I'm an Electrical Engineer from the University of Brasília, now a Research Scholar at The University of Tokyo
Originally from Brasília, the capital of Brazil, I am fluent in both English and Portuguese, with some proficiency in Spanish, and I am currently learning Japanese as I live in Japan. As a research scholar, I focus on studying foundational models and recommender systems.
Through this blog, I aim to share my knowledge and insights to help others on their learning journey, particularly, on artificial intelligence and its applications.
Latest Posts
- Osaka 大阪 | Kyoto 京都 | Nara 奈良A short list of picks form the three times I’ve been there 🚨 General Tips: 🎏 Osaka Regarding restaurants I don’t have a lot of recommendations except for… Toyo – Location If you’re into amusement parks, I really recommend Universal Studios, especially for the Super Nintendo World area. 🦌 Nara I highly recommend visiting Nara! You’ll… Read more: Osaka 大阪 | Kyoto 京都 | Nara 奈良
- Tokyo 東京My favorite corners of Tokyo. Hopefully this list will keep growing over time 🙂 🚨 General Tips: 🐟 Sushis Tips: Restaurants I like: 🍜 Ramen / Lamen Tip: Ramen is probably the best value-for-money food in Japan. But in Tokyo, some places are tourist traps, so again, follow the Google rating (> 4.1) and check… Read more: Tokyo 東京
- A Causality Summary Part IIIMain Reference: https://arxiv.org/abs/2405.08793 Learning in Latent Variable Models Latent variable models are powerful extensions of probabilistic models. They introduce hidden or unobserved variables to explain dependencies in data that cannot be captured solely by observed variables. These latent variables often represent underlying processes or structures that are not directly measurable. Latent Variable Representation Given a… Read more: A Causality Summary Part III
- A Causality Summary Part IIMain Reference: https://arxiv.org/abs/2405.08793 Probabilistic Graphical Models Probabilistic Graphical Models (PGMs) are powerful tools that represent the joint probability distribution of a set of random variables in terms of their conditional dependencies, which are typically defined by a graph structure. A fundamental task in PGMs is sampling from the joint distribution, and this can be achieved… Read more: A Causality Summary Part II
- A Causality Summary Part IMain Reference: https://arxiv.org/abs/2405.08793 Have you ever thought about the word “causal” in the sentence we’ve all heard: “Smoking causes lung cancer”? It sounds pretty simple, right? The way I see it, at least, is the following: if someone has lung cancer and they smoke, we assume smoking caused it. smoke — causes —> cancer Okay, but… Read more: A Causality Summary Part I
