How it is possible to drastically reduce the data annotation effort

Photo by Bernard Hermant on Unsplash

In the previous posts I showed how we managed to train a neural network to detect objects with a very small number of annotated examples, now I will tell you what is our “secret”.

A Deep Neural network is a software/mathematical artifact that converges from a dataset to an algorithm that model that data. It’s an intrinsically very complex process, but if we intuitively understand its inner workings, we can understand how to guide neural network convergence/learning to quickly achieve optimal results.

The key point that I consider fundamental…

Or: Why Neural Networks are so revolutionary

Photo by Nathan Anderson on Unsplash

Before the advent of modern deep learning, images and sounds were unstructured data files, there was no way computers could interpret their contents. The computer vision area was dominated by algorithms focused on the use of hand-crafted functions that sought to interpret the geometric elements that made up the images. The assertiveness of these algorithms was very low, and the applications were restricted to environments with very controlled conditions.

Several research institutes promoted challenges for the development of new algorithms which could interpret the content of images, being the most famous of them…

Or How can an AI learn with very few examples

Photo by Docusign / Unsplash

I often see a lot of people talking about how an AI project can be an extremely laborious task because it needs thousands of annotated examples to train well the neural network.

This may be true to some scopes, where there is great variability in the object of detection, like, for example, in the ImageNet dataset, with 1000 classes in extremely different environments. But, in quality inspection projects, usual here at Eyeflow.AI, …

How 4 years of pitfalls drove us to developer a great tool for the job

An wood bridge between trees
An wood bridge between trees
Photo by Ronaldo de Oliveira on Unsplash

In 2016 I was invited by a friend for a challenge: to develop a video analytics solution for a large Brazilian mining company. I have always been passionate about artificial intelligence. I have been following the topic since 1995, and was looking for applications for machine learning and deep learning since 2011, so I took the challenge right away.

The task seemed quite complex: capturing images of ore transport wagons using video cameras to automate the components inspection and detect failures.

I’m a very skilled…

Alex Sobral de Freitas

Founder, Architect, AI Engineer, Philosopher

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store