Sometimes writing your own algorithm out-performs a library by 3 orders of magnitude
Vortexa’s CEO Fabio Kuhn delivered a presentation on Scaling Human Energy Market Expertise with AI, as part of ZE Powergroup’s Global Tech Summit. In the presentation, he discussed the digitisation of the industry and how this affects making faster and smarter trading decisions.
Using Data Science to create unprecedented visibility into energy markets and make the world slightly better.
This is the second article of this series, outlining how to think about data processing code in the Python world, and more specifically, how we can improve our code performance while writing legible, maintainable, production-quality code.
In this article, our Head of Data Services focuses on different practices to make sure that our data can be trusted, how we keep it recent and always accessible by adopting the mindset of site reliability engineering.
A look into the journey of one of our analysts learning Python and implementing his skills with the Vortexa SDK.
The first in a two-part series of articles outlining how to think about data processing code in the Python world, and how we can improve our code performance while writing legible, maintainable, production-quality code.
The final chapter of our Satellite Image Segmentation. This piece is an analysis on how to identify where ships are within a satellite image, building a U-Net from the encoder developed in Part 2.
Towards a fully convolutional network, for more interpretability (example of CAM attention), early localisation properties, and capability to evolve into an image segmentation model. In the process, we’ll delve into the technique of transfer learning.