Deep Learning

Detailed tutorial explaining how to efficiently train the object detection algorithm YOLOv5 on your own custom dataset. — Introduction Identification of objects in an image considered a common assignment for the human brain, though not so trivial for a machine. Identification and localization of objects in photos is a computer vision task called ‘object detection’, and several algorithms has emerged in the past few years to tackle the problem…

Stable Diffusion makes for a very powerful lossy image compression codec. — Intro Stable Diffusion is currently inspiring the open source machine learning community as well as upsetting artists world wide. I was curious to see what else this impactful technology release could be used for other than making professional artists and designers ponder their job security. While experimenting with the model, I…

The expressive power of Message-Passing Graph Neural Networks is inherently limited due to their equivalence to the Weisfeiler-Lehman graph isomorphism test. Several concurrent recent works show that this limitation can be overcome by applying a GNN on a collection of subgraphs obtained by removing nodes or edges from the input graph. In this post, we review the common themes and nuances of these different approaches.

Who doesn’t love a good explainer? Some of our favorite reads on TDS are those that take complex topics and translate them into accessible—and very often, actionable—knowledge. This week, we’re thrilled to share a selection of articles that tackle questions at the forefront of current research on deep learning and…

Using LSTM networks for time series prediction and interpreting the results — Forecasting, making predictions about the future, plays a key role in the decision-making process of any company that wants to maintain a successful business. This is due to the fact that success tomorrow is determined by the decisions made today, which are based on forecasts. …