teaching

PyTorch

• PyTorch Challenges: a set of 27 mini-puzzles (extension of the ones proposed by Sasha Rush)
• From Puzzles to Real Code: examples of broadcasting in real word applications: wordpieces aggregation, clustered attention, attention statistics.

ML for NLP (work in progress)

• ml-for-nlp-course: a theoretical revision of ML alongside practical implementations. Right now it includes interactive notebooks for learning the basics: linear algebra, statistics, and optimization.

Teacher Assistant in Deep Structured Learning (IST)

I was a TA for the course of Deep Structured Learning (2020) at IST. I was responsible for helping in grading, creating homeworks, and providing code solutions to students. I also gave two guest lectures:

• A PyTorch Tutorial
• Neural Attention Mechanisms

Guest Talks

• “Transformers” in the Advanced Spoken Language Processing Seminar course at IST.
• “Prediction Explainability through Sparse Communication” in the Priberam Machine Learning Seminar.
• “O fim das word embeddings? From BOW to BERT” in the NLP in 20 Slides Seminar at ICMC/USP.

Lisbon Machine Learning School Monitor

I was a monitor of the Lisbon Machine Learning School on two editions, one in 2018 and another in 2019. I was responsible for answering questions and helping out students during the PyTorch Lab sessions.