Deep learning review and its applications

Deep neural networks have recently gained popularity for improv- ing state-of-the-art machine learning algorithms in diverse areas such as speech recognition, computer vision and bioinformatics. Convolutional networks especially have shown prowess in visual recognition tasks such as object recognition and detection in which this work is focused on. Mod- ern award-winning architectures have systematically surpassed previous attempts at tackling computer vision problems and keep winning most current competitions. After a brief study of deep learning architectures and readily available frameworks and libraries, the LeNet handwriting digit recognition network study case is developed, and lastly a deep learn- ing network for playing simple videogames is reviewed.

Comparative study of human age estimation based on hand-crafted and deep face features

In the past few years, human facial age estimation has drawn a lot of attention in the computer vision and pattern recognition communities because of its important applications in age-based image retrieval, security control and surveillance, biomet- rics, human-computer interaction (HCI) and social robotics. In connection with these investigations, estimating the age of a person from the numerical analysis of his/her face image is a relatively new topic. Also, in problems such as Image Classification the Deep Neural Networks have given the best results in some areas including age estimation. In this work we use three hand-crafted features as well as five deep features that can be obtained from pre-trained deep convolutional neural networks. We do a comparative study of the obtained age estimation results with these features.

Análisis predictivo para clasificar dígitos escritos a mano utilizando la base de datos MNIST

En el presente trabajo de fin de máster se realiza una investigación sobre las técnicas de preproceso del dataset de entrenamiento y la aplicación de un modelo de predicción que realice una clasificación de dı́gitos escritos a mano. El conjunto de dataset de train y test son proporcionado en la competencia de Kaggle: Digit Recognizer y provienen de la base de datos de dı́gitos manuscritos MNIST. Por tratarse de imágenes las técnicas de preproceso se concentran en obtener una imagen lo más nı́tida posible y la reducción de tamaño de la misma, objetivos que se logran con técnicas de umbralización por el método de Otsu, transformada de Wavelet de Haar y el análisis de sus componentes principales. Se utiliza Deep Learning como modelo predictivo por ajustarse a este tipo de datos, se emplean además librerı́as de código abierto implementadas en el lenguaje estádisto R. Por último se obtiene una predicción con las técnicas y herramientas mencio- nadas para ser evaluada en la competencia de Kaggle, midiendo y comparando los resultados obtenidos con el resto de participantes.