Publications - Neural networks

Structured Text Generation for Spanish Freestyle Battles using Neural Networks
Conference paper

As the presence of artificial intelligence has increased in a variety of different areas, the use of machine learning and deep learning techniques for creative purposes has also risen significantly in recent years. We designed a neural network-based generation model that takes into account both the structure of freestyle and the low data availability. The model was able to generate realistic freestyle verses in Spanish.

Deep learning Adaptation models Computational modeling Neural networks Natural language processing Generators Data models

A Comparison of Neural Networks for Sign Language Recognition with LSA64
Conference paper

We evaluate three models built on standard recurrent and convolutional neural network layers on LSA64. Coupled with carefully chosen hyperparameters and preprocessing techniques, these models are all able to achieve near perfect accuracy on LSA64, surpassing all previous models, many specifically designed for this task.

Sign language recognition Neural networks LSA64 Convolutional neural networks Recurrent neural networks Computer vision

Structured Text Generation for Spanish Freestyle Battles using Neural NetworksConference paper

A Comparison of Neural Networks for Sign Language Recognition with LSA64Conference paper

Structured Text Generation for Spanish Freestyle Battles using Neural Networks
Conference paper

A Comparison of Neural Networks for Sign Language Recognition with LSA64
Conference paper