Recent speech recognition advances on the SWITCHBOARD corpus suggest that because of recent advances in Deep Learning, we now achieve Word Error Rates comparable to human listeners. Does this mean the speech recognition problem is solved and the community can move on to a different set of problems?
The 20th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL) is an annual international conference dedicated to emerging and challenging topics in intelligent data analysis, data mining and their associated learning systems and paradigms.
In this talk, we propose item and user-based Fuzzy Collaborative Filtering approaches that do not necessarily rely on rating prediction, instead leveraging on Fuzzy Fingerprints to create a novel similarity based recommendation approach. Fuzzy Fingerprints provide a concise and compact representation of users allowing the reduction of the dimensionality usually associated with user-based collaborative filtering.
Structural adhesive bonding is used in many critical applications, but the performance of such joints relies on the integrity of the bond between adhesive and substrate. Such bonding involves layers only a few atoms thick and this talk will consider how surface analysis methods are able to provide us with analytical information which will lead to optimum performance in the most demanding of applications.