Processando dados não estruturados com aprendizado profundo

Processing unstructured data with deep learning

Each type of data presents a new problem for data scientists and analysts, who need to figure out the best way to collect and clean it before it is analyzed.

Imagem em destaque

Tesseract is an OCR tool that uses deep learning to recognize words in images, which, as simple as it may seem, can actually be a very complex task.

For example, some images might be in low definition, or maybe the text is out of focus, or maybe it's part of a video and only has a few frames. In other words, each image is a world of its own, and instead of creating an algorithm for each case, we use deep learning to work with all images at once, saving time and effort.

We live in an unstructured world and humans rarely think in terms of structured data, as such, deep learning has become one of the most important AI tools in the technology industry. To be fair, it's still in its infancy, but it's only a matter of time before Siri and similar apps become something more than glorified search engines.

Source: BairesDev

Back to blog

Leave a comment

Please note, comments need to be approved before they are published.