GPU based Self Organizing Maps for Post Labeled Few Shot Unsupervised Learning

Few-shot classification is a challenge in machine learning where the goal is to train a classifier using a very limited number of labeled examples . This scenario is likely to occur frequently in real life, for example when data acquisition or labeling is expensive . To address this problem, we consider an algorithm consisting of the concatenation of transfer learning with clustering using Self-Organizing Maps (SOMs) We introduce a TensorFlow-based implementation to speed-up the process in multi-core CPUs and GPUs . Finally, we demonstrate the effectiveness of the method using standard off-the-shelf classification benchmarks. The method is shown to be effective on standard off the shelf few-shot classifications benchmarks. It is designed to speed up the process

Links: PDF - Abstract

Code :

Keywords : shot - learning - organizing - labeled - process -

Leave a Reply

Your email address will not be published. Required fields are marked *