Understanding Zero Shot Learning

Exploring the different types of zero-shot learning methods.

Image Source: https://alibabatech.medium.com/from-zero-to-hero-shaking-up-the-field-of-zero-shot-learning-c43208f71332

I recently started an AI-focused educational newsletter, that already has over 125,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Please give it a try by subscribing below:

TheSequence

The deep learning world have recently seen a proliferation of techniques that try to learn without relying on large labeled datasets. Among those, zero-shot learning(ZSL) has become very popular among large AI labs. Conceptually, ZSL belongs to the family of N-shot learning methods which are extremely useful in scenarios with small labeled datasets for training. Specifically, ZSL tackles a type of problem in which the learner agent is able to classify data-instances from classes not seen during training. It is important to notice that ZSL is not a form of unsupervised learning. ZSL models are supervised methods that are effectively trained but they are able to…