altolending

Recently, Sesame AI published a demo of their latest Speech-to-Speech model. A conversational AI agent who is really good at speaking, they provide relevant answers, they speak with expressions, and honestly, they are just very fun and interactive to play with. Note that a technical paper is not out yet, but they do have a […]

In my previous articles, I have spent a lot of time talking about the technical aspects of an Image Classification problem from data collection, model evaluation, performance optimization, and a detailed look at model training. These elements require a certain degree of in-depth expertise, and they (usually) have well-defined metrics and established processes that are within our control. Now it’s time

This article is co-authored by Felipe Bandeira, Giselle Fretta, Thu Than, and Elbion Redenica. We also thank Prof. Carl Scheffler for his support. Introduction Parameter estimation has been for decades one of the most important topics in statistics. While frequentist approaches, such as Maximum Likelihood Estimations, used to be the gold standard, the advance of

Liberating education consists in acts of cognition, not transferrals of information. Paulo freire One of the most heated discussions around artificial intelligence is: What aspects of human learning is it capable of capturing? Many authors suggest that artificial intelligence models do not possess the same capabilities as humans, especially when it comes to plasticity, flexibility,

In a world that focuses more on data, business leaders must understand vector thinking. At first, vectors may appear as complicated as algebra was in school, but they serve as a fundamental building block. Vectors are as essential as algebra for tasks like sharing a bill or computing interest. They underpin our digital systems for

Ground truth is never perfect. From scientific measurements to human annotations used to train deep learning models, ground truth always has some amount of errors. ImageNet, arguably the most well-curated image dataset has 0.3% errors in human annotations. Then, how can we evaluate predictive models using such erroneous labels? In this article, we explore how

Did you ever spend months on a Machine Learning project, only to discover you never defined the “correct” problem at the start? If so, or even if not, and you are only starting with the data science or AI field, welcome to my first Ivory Tower Note, where I will address this topic.  The term

Introduction I’ve always been fascinated by debates—the strategic framing, the sharp retorts, and the carefully timed comebacks. Debates aren’t just entertaining; they’re structured battles of ideas, driven by logic and evidence. Recently, I started wondering: could we replicate that dynamic using AI agents—having them debate each other autonomously, complete with real-time fact-checking and moderation? The

Gradient boosting is a cornerstone technique for modeling tabular data due to its speed and simplicity. It delivers great results without any fuss. When you look around you’ll see multiple options like LightGBM, XGBoost, etc. Catboost is one such variant. In this post, we will take a detailed look at this model, explore its inner

I used to avoid time series analysis. Every time I took an online course, I’d see a module titled “Time Series Analysis” with subtopics like Fourier Transforms, autocorrelation functions and other intimidating terms. I don’t know why, but I always found a reason to avoid it. But here’s what I’ve learned: any complex topic becomes