Seminar of Cognitive Science - Matúš Tuna (24.4.2018)
Tuesday 24.4.2018 at 16:30, Lecture room I/9
By: Igor Farkaš
Mgr. Ing. Matúš Tuna:
Few shot learning in artificial neural networks
Artificial neural networks recently became the most successful approach in machine learning with many successful applications in various domains such as image recognition, machine translation, reinforcement learning or generative modeling. The majority of artificial neural network models are currently trained using the gradient descent method with an error backpropagation mechanism. However, the main disadvantage of these models is the required large number of training examples for achieving reasonable performance. This limits the applications to domains offering abundance of labelled training examples or, in the case of reinforcement learning, the large number of interactions with an environment makes it possible to learn the task in that environment. In this talk, we will explore the few-shot learning approach, requiring only a few labeled examples and review various few-shot learning methods based on artificial neural networks. We will also propose a novel approach to the few-shot learning approach called Categorical Siamese neural networks.