This thesis develops a novel methodology incorporating symbolic knowledge in deep learning. We

learning and computer vision. Over the last decade, deep neural networks have achieved remarkable success

to significant performance improvement. However, the insight about why and how deep learning models

Characterizing Pulmonary Nodules using Machine and Deep Learning Methods to Improve Lung Cancer

Over the past decade, a machine learning technique called deep-learning has gained prominence in

performances were then compared with a deep learning technique's, the Long Short Term Memory-Recurrent Neural

traditional machine learning algorithms to the deep learning method. The results we calculated show that the

-critical decisions such as perception for self-driving cars, the machine learning community has been extremely

choices and ratings. Even the machine learning-based existing recommender systems are mainly based on pre

notion in machine learning theory. We will show how, in the regime of deep learning, the characterization

, the capabilities of different feature categories and advanced machine learning techniques have not

speech domain, most deep architectures have used a Restricted Boltzmann Machine (RBM) based deep