Published inGumGum Tech BlogOvercoming the shortcomings of translated data when building an NLP classifierImagine this: you are designing a natural language processing (NLP) classifier to identify whether a particular brand is mentioned in a…Dec 27, 20241Dec 27, 20241
Published inGumGum Tech BlogAn easy recipe for multi-task learning in PyTorch that you can do at homeIn my last blogpost, I touched on what multi-task learning is, how it works, and why it is becoming the de facto standard for machine…Dec 27, 20224Dec 27, 20224
Published inGumGum Tech BlogMulti-task learning: what is it, how does it work and why does it work?One of the most exciting and seemingly ubiquitous recent topics in deep learning (DL) is without a doubt multi-task learning. Multi-task…Nov 11, 20223Nov 11, 20223
How advantageous is Advantage in D&D 5e?Man, I love D&D 5e. I got my first set back at the end of the TSR days and I’ve been playing regularly since early in the 4e days and I can…Sep 9, 20221Sep 9, 20221
Is this coin, die or whatever even fair?Tell me if this has happened to you. You notice that the coin you and your partner flip to decide who washes the dishes seems to land on…Sep 6, 2022Sep 6, 2022
Published inGumGum Tech BlogCreating a balanced multi-label dataset for machine learningOne of the challenges that we encounter when dealing with imbalanced data in a multi-label classification problem and a novel solution.Mar 4, 2022Mar 4, 2022
