Welcome to the Abacus.AI blog

We have been working on various experiments related to extending the context of pretrained models. In the post we share links to a repository with code and hugging face models and datasets.

In this blog post, we discuss Abacus.AI’s NeurIPS 2022  paper on recommender systems.Paper: https://arxiv.org/abs/2206.11886Code: https://github.com/naszilla/reczilla1 min video: https://www.youtube.com/watch?v=Eu8G3oNzcvU5 min video: https://www.youtube.com/watch?v=NkNdxF5chZY The concept of meta-learning is both simple and powerful: information about the past performance...

In our previous post, we presented an introduction to Seq2Seq models – models that take a sequence as an input and produce a sequence for their output. Back in 2014, they revolutionized the field of...

When reading about Machine Learning, the majority of the material you’ve encountered is likely concerned with classification problems. You have a certain input, and the ML model tries to figure out the features of that...

Most of the machine learning applications are concerned with processing data such as images or databases – their key characteristic is that they can be “taken in” by a learning model all at once. They don’t have any temporal properties. Today we’ll be talking about a different case – models that deal with data that is sequential by nature, text, and voice being several examples.

When reading about Machine Learning, the majority of the material you’ve encountered is likely concerned with classification problems. What about the other way around when you want to create data with predefined features? Today we’ll be breaking down VAEs and understanding the intuition behind them.

Pattern recognition is a crucial aspect of modern data analytics. These patterns can be studied to better understand the underlying structure of data and monitor behavior over time. However, there are often rare items or observations that seem to differ significantly from these patterns. These items are called anomalies (or outliers).

The painting “Edmond de Belamy” is an AI-generated portrait that was sold at an auction for $432,500 in 2018. That’s a lot of money for an artificial painting, but how exactly was it created? Generative Adversarial Networks.

I. Rules and progression to machine learning including probabilistic modeling (Naïve Bayes and Conditional Random Fields) The field of Natural Language processing has come a long way thanks to the contributions of many people...