We can turn a simple autoencoder into something sophisticated. Autoencoders discover a latent mapping z, which as a lower-dimensional representation of the input x, can be useful for pre-training networks and creating recommender models. However, how autoencoders compress information may come in millions of ways. To truly polish how z can be generated, we turn […]
Opinion piece on Leni, and the Philippine elections
Medicine is quite different from my profession but I think having this kind of interest is healthy (get it?). Eventually, I came to reach some parallels between my discipline and the medical sciences.
Autoencoders are a simple neural network approach to recommendation
Variational autoencoders can discover unique ways to encode-decode the input from a distribution. Bonus: It can generate images!
Back in college, I did a class project where I used computer vision techniques for the first time. It was the age before deep learning. Today, I want to revisit this old project.
A tutorial to create a recommender pipeline with Kedro and MLFlow.
An uploaded family photo inspired me to pick up a colorizer tool. Here is my post honoring my family’s history.
MLOps is all about creating sustainability in machine learning. To maintain structure in this fast-paced field, you can try out Kedro, an open-source Python project that aims to help ML practitioners create modular, maintainable, and reproducible pipelines.
This is part 2 of my talk on recommenders. The presentation describes the intuitions of matrix factorization and how to implement it in R. I delivered this in the R-Users Group PH meetup group this November. If you wish to see some more recommender material in this blog, check this out: