In this paper, we suggest to use a steepest descent algorithm for learning a parametric dictionary in which the structure or atom functions are known in advance. The structure of ...
Mahdi Ataee, Hadi Zayyani, Massoud Babaie-Zadeh, C...
As Technology Enhanced Learning (TEL) systems become more essential to education there is an increasing need for their creators to reduce risk and to design for success. We argue t...
An enhanced self-organizing incremental neural network (ESOINN) is proposed to accomplish online unsupervised learning tasks. It improves the self-organizing incremental neural ne...
How humans infer probable information from the limited observed data? How they are able to build on little knowledge about the context in hand? Is the human memory repeatedly const...
Causal learning methods are often evaluated in terms of their ability to discover a true underlying directed acyclic graph (DAG) structure. However, in general the true structure ...
David Duvenaud, Daniel Eaton, Kevin P. Murphy, Mar...