Simultaneous Perturbation Stochastic Approximation for Few-Shot Learning
This work addresses the uncertainty in few-shot learning for machine learning applications, but it appears incremental as it builds upon existing prototypical networks.
The paper tackled the problem of few-shot learning, where classifiers must adapt to new classes with limited examples, by proposing a new multi-task loss function and an SPSA-like approach based on prototypical networks, resulting in superior performance over the original prototypical networks on benchmark datasets.
Few-shot learning is an important research field of machine learning in which a classifier must be trained in such a way that it can adapt to new classes which are not included in the training set. However, only small amounts of examples of each class are available for training. This is one of the key problems with learning algorithms of this type which leads to the significant uncertainty. We attack this problem via randomized stochastic approximation. In this paper, we suggest to consider the new multi-task loss function and propose the SPSA-like few-shot learning approach based on the prototypical networks method. We provide a theoretical justification and an analysis of experiments for this approach. The results of experiments on the benchmark dataset demonstrate that the proposed method is superior to the original prototypical networks.