Published inTDS ArchiveAchieving a top 5% position in an ML competition with AutoMLAutoML pipelines are a hot topic. The general goal is simple: enable everyone to train high-quality models specific to their business…May 2, 20192May 2, 20192
Published inTDS ArchiveMachine learning interpretability techniquesMost machine learning systems require the ability to explain to stakeholders why certain predictions are made. When choosing a suitable…Mar 14, 20194Mar 14, 20194
Published inTDS ArchiveCommon data science pitfalls and how to avoid themDuring my studies I had the opportunity to work on several machine learning research projects. These projects ranged from studying…Jul 20, 20181Jul 20, 20181
Published inTDS ArchiveUnderstanding model predictions with LIMEIn my previous post on model interpretability, I provided an overview of common techniques used to investigate machine learning models. In…Jul 11, 201811Jul 11, 201811
Published inTDS ArchiveGoing deep into object detectionWith recent advancements in deep learning based computer vision models, object detection applications are easier to develop than ever…Apr 23, 20189Apr 23, 20189
Published inTDS ArchiveGoing deep into image classificationLearning about the different network architectures for image classification is a daunting task. In this blog post I will discuss the main…Mar 28, 20184Mar 28, 20184
Published inTDS ArchiveInterpreting machine learning modelsRegardless of the end goal of your data science solutions, an end-user will always prefer solutions that are interpretable and…Feb 20, 201811Feb 20, 201811
Published inTDS ArchiveApplying transfer learning in NLP and CVIn this blog post I will discuss two applications of transfer learning. I will provide an overview of examples in the field of natural…Jan 22, 20183Jan 22, 20183
Published inTDS ArchiveTransfer learning: leveraging insights from large data setsIn this blog post, you’ll learn what transfer learning is, what some of its applications are and why it is critical skill as a data…Jan 22, 20184Jan 22, 20184
Published inTDS ArchiveGradient descent vs. neuroevolutionIn March 2017, OpenAI released a blog post on evolution strategies, an optimisation technique that has been around for several decades. The…Dec 20, 20175Dec 20, 20175