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: deep learning
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 […]
Autoencoders are a simple neural network approach to recommendation
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.
My Heritage In Color
An uploaded family photo inspired me to pick up a colorizer tool. Here is my post honoring my family’s history.
In this video, I’ll discuss my solution to the SIIM-ISIC Melanoma Classification Challenge hosted in Kaggle.
Hi all! I’m trying out this new format of publishing my projects through Powerpoint videos. Recording this way is fun. Let me know if this is a better format for you. This pet project is my tribute to books. As a machine learning person, I’d like to see if I can artificially create images of […]
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!
Time for another vision blog. Here, I’ll talk about dogs. Humans can identify a dog from a cat well enough, but it’s a little harder to distinguish specific dog breeds. For instance, can you tell which is which in the following? Well, on the left is a Siberian Husky and on the right is an […]
Hello Deep Learning!
Another interesting thing about deep learning is, being inspired by neural networks, it is similar to how our brains work. Our brains have different areas for different stimuli, and our neurons combine these signals hierarchically.