I’m going to use NVTabular with PyTorch Lightning to train a wide and deep recommender model on MovieLens 25M. It’s quite a chimera implementation as you shall see.
Tag: python
Categories
NVIDIA Merlin on a Potato PC Setup
NVIDIA Merlin is a high-level open-source library to accelerate recommender systems on NVIDIA GPUs at scale. I’m on a potato PC setup relying on free instances. Can I make it work?
Header image note: I typed ‘variation’ in Pexels and it popped up. Masarap! 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 […]
Variational autoencoders can discover unique ways to encode-decode the input from a distribution. Bonus: It can generate images!
A tutorial to create a recommender pipeline with Kedro and MLFlow.
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.
Today I will be taking a look at blood chemistry tests and COVID-19. I am trying to see associations of the different blood cell types when there is a SARS-COV-2 infection. I am joined with my friend Dr. Earl Tiu as I try to explain my findings to him. The data is sourced from Kaggle, […]
I had the opportunity to again host a Kaggle-like competition. Here is how I would have solved my own problem and how user’s preferences apply in e-commerce.
If a computer would have eyes, what would it be able to recognize? Distinguishing cats and dogs would be nice, but what’s better is recognizing all 7,870 objects in the Open Images dataset!
I’ve been tinkering with customer lifetime value modeling the past few days since the Olist dataset in Kaggle went up. In particular, I wanted to explore the tried and tested probabilistic models, BG/NBD and GammaGamma to forecast future purchases and profits. I also wanted to see if the machine learning approach could do well — […]
It is the REAL DYL 