Category: Technical

Unlocking Business Success with Langchain: The Power of Smart Document Summarization

Imagine a bustling corporate boardroom where executives, armed with stacks of reports and documents, gather for a high-stakes decision-making meeting. The clock is ticking, and the pressure is palpable. In the midst of this chaos, there’s an untapped opportunity—a way to transform this situation from a time-consuming ordeal into a seamless, efficient process. Welcome to […]

Written by on Dec 2, 2023

Customizing Language Models: Fine-Tuning vs. Prompt Engineering

In the rapidly evolving landscape of artificial intelligence, there’s a notable surge in interest and activity surrounding generative AI. The question arises: Why this rush? What’s the driving force? The answer lies in the transformative power of customizing Large Language Models (LLMs). Businesses are increasingly captivated by the potential these models hold, specifically when tailored […]

Written by on Nov 6, 2023

Unleashing the Power of Open-Source Geospatial Data

Information is power, and geospatial data plays a vital role in various fields, including urban planning, transportation, environmental studies, and more. With the advent of machine learning, the demand for high-quality geospatial datasets has grown exponentially.  In the midst of this, you will find a lot of tools and product owners that will ask for […]

Written by on Oct 10, 2023

Classifying text using LLMs

  Text classification is one of the most common use cases in Natural Language Processing, with numerous practical applications – now easier to access with Large Language Models. Companies use text classification in multiple scenarios to become more efficient: Tagging large volumes of data: reducing manual labor with better filtering, automatically organizing large volumes of […]

Written by on Aug 29, 2023

Making Money with Mediocre AI Models

In the world of AI, it’s easy to assume that only the most accurate models can bring value to your business. However, this is far from the truth. In fact, even mediocre models can be transformed into money-making machines with the right strategies. In this article, we’ll explore three real-life examples of how we turned […]

Written by on Aug 15, 2023

Spatial Explanations: Unlocking Insights with Occlusions

Spatial Explanations with Occlusions: In computer vision, businesses must grasp the workings of image models to fully leverage visual data. Our simple method called spatial explanations with occlusions, helps achieve a deeper understanding. By employing spatial occlusions across images, this technique unveils critical areas that significantly influence the model’s predictions.” What to do with these […]

Written by on Aug 2, 2023

Protect your AI Model from attackers!

Machine learning models can achieve amazing results performing tasks they were designed to. They can also have catastrophic performance if the data we feed the model is not compliant with the data used to train it. This can be exploited as an adversarial attack on our model. Adversarial attacks are a common and growing problem […]

Written by on Jul 10, 2023

In medio stat virtus? Not always!

The Problem What do you do when the model is underperforming? When the models’ performance does not meet our expectations, we usually spend time searching for the flaws, selecting and analyzing the cases where it failed to understand why it happened. Then, we try to apply more robust solutions, train, test, and repeat. In some […]

Written by on Apr 10, 2023

Increasing Efficiency with Active Learning

The problem: Labeling data is boring (and expensive) So there you are. You have collected your data, analyzed it, processed it, and built your sophisticated model architecture. After many hours of training and evaluating, you have come to a very unpleasant conclusion: you need more data. Before you readjust your budget to fit the extra […]

Written by on Mar 3, 2023

How to deal with the annoying implications of changing data sources

Let’s discuss a common scenario in AI consulting. The client provides access to data sources in formats such as CSVs or databases that aren’t in a production environment. Why? Usually, they’re exploring the value of the project, do not want to disclose too much data and want to prevent technical problems from happening at the […]

Written by on Nov 20, 2022