The use of deep learning to solve the problems in literary arts has been a recent trend that gained a lot of attention and automated generation of music has been an active area. This project deals with the generation of music using raw audio files in the frequency domain relying on various LSTM architectures. Fully connected and convolutional layers are used along with LSTM’s to capture rich fe...

A blind learner needs some method other than Venn diagrams to test syllogisms for validity. I present here a sketch of a three-dimensional apparatus, Sylloid, invented to fill this need and to inculcate deep learning rather than the mere ability to get answers right. What one learns in the design process is then used in designing a successor, Son of Sylloid, for sighted users that is pedagogica...

One of the main challenges in teaching and learning activities is the assessment: it allows teachers and learners to improve the future activities on the basis of the previous ones. It allows a deep analysis and understanding of the whole learning process. This is particularly difficult in virtual learning environments where a general overview is not always available. In the latest years, Learn...

Deep Learning networks have sharply increased over the past 10 years, and deep Learning-Based Classification of Remote Sensing Image has attracted extensive interest. We trained a multilayer deep learning network to classify the 8 thousand unlabeled remote sensing images from Internet into the 600 different classes. In order to improve the efficiency, and shorten the experiment time, we also us...

Deep learning is a branch of artificial intelligence where networks of simple interconnected units are used to extract patterns from data in order to solve complex problems. Deep learning algorithms have shown groundbreaking performance in a variety of sophisticated tasks, especially those related to images. They have often matched or exceeded human performance. Since the medical field of radio...

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively l...

Along with the rapid development of deep learning in practice, theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning. The expressivity focuses on finding functions expressible by deep nets but cannot be approximated by shallow nets with the similar number of neurons. It usually ...

Our team has worked on melanoma classification since early 2014 [1], and has employed deep learning with transfer learning for that task since 2015 [2]. Recently, the community has started to move from traditional techniques towards deep learning, following the general trend of computer vision [3]. Deep learning poses a challenge for medical applications, due to the need of very large training ...

In this paper we present a domain adaptation technique for formant estimation using a deep network. We first train a deep learning network on a small read speech dataset. We then freeze the parameters of the trained network and use several different datasets to train an adaptation layer that makes the obtained network universal in the sense that it works well for a variety of speakers and speec...