Olga Petrova

In today's data-driven world, GPUs are the hardware of choice for training Deep Learning models. What about tasks that do not involve artificial neural networks? For instance, is there a benefit to using a GPU for making product recommendations? Continue reading to find out!

This blog post is the continuation of "Active Learning, part 1: the Theory", with a focus on how to apply the said theory to an image classification task with PyTorch.

Active learning is still a niche approach in machine learning, but that is bound to change. After all, active learning provides solutions to not one, but two challenging problems that have been poisoning the data scientists' lives. Those are, of course, the data: its (a) quantity and (b) quality.

Semi-supervised machine learning is a solution when labeled data is scarce. In the article we introduce a semi-supervised Generative Adversarial Network for image classification. Read on to find out how to get a 20% increase in accuracy when distinguishing cats and dogs with only 100 labeled images!

How to build a machine reading comprehension system using the latest advances in deep learning for NLP.