Deep Learning

Art Style Classification with Self-Trained Ensemble of AutoEncoding Transformations

Investigation on the use of deep semi-supervised neural models to extract dense features in complex & ambiguous images spanning across 27 unique artistic styles. Self-supervision enforced to resolve class imbalance of WikiArt dataset

Learning like humans with Deep Symbolic Networks

Amalgamating the reasoning power of Symbolic AI with the learning ability of Deep Neural Networks as part of Hybrid Machine Learning Approaches and Applications Seminar