Decision boundaries are imposible to be visualized in hogh dimensional feature sets. Instead of visualizing them, we can characterize them and make them useful.
Neural networks have a bad reputations as they are treated like black boxes and lack interpretations on the results they make. Grad-CAM can slightly interprete what is driving the model to make a decision.
Enhancement of accuracy for wrist-worn sensor based lying posture classification via transfer learning
Optimization Algorithms to begin with Sparse Coding.
Exploring traditional GAN and semi-supervised GAN and identify key dissimilarities
Finding the best structure of a Multi-task Learning Network given a set of related/unrelated tasks
Task relation assessment and setting MTL parameters according to task groups
Modulate the width of the network efficiently
