Wordnet y Deep Learning: Una posible unión

Autor: Raquel Leandra Pérez Arnal

Directores: Dario Garcia Gasulla y Claudio Ulises Cortés García

Abstract

Convolutional neural networks (CNN) are representation learning techniques that achieve state-of-the-art performance on almost every image-related, machine learning task. Applying the representation languages build by these models to tasks beyond the one they were originally trained for is a field of interest known as transfer learning for feature extraction. In this work we will study a Full-Network Embedding made ussing transfer learning from a deep convolutional neural network trained for image classification ussing the dataset of Imagenet and it’s rellation with different synsets of Wordnet.