Hey there everyone, hope everyone’s having a fantastic Friday 😊 Today we’ll discuss active learning and show you some cool things that can be done using our active learning interface. Active learning is useful especially in situations where there is a lot of data to be labelled, which can be prioritised to label the data in an efficient manner. In our active learning interface, you can apply few-shot learning for heuristics. These are very valuable for weak supervision as you can integrate them with labeling functions or other heuristics. We integrate HuggingFace embeddings so you can use your favourite transformer models for embeddings. They typically require only little training data to get a reasonable precision.
If you want to learn more about this, we have uploaded a full tutorial on our Youtube channel, check it out here - https://www.youtube.com/watch?v=VfQapj5TtUQ&ab_channel=KernAI
Subscribe to our newsletter 👉🏼 https://www.kern.ai/pages/open-source and stay up to date with the release so you don’t miss out on the chance to win a GeForce RTX 3090 Ti for our launch
Top comments (0)