TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise

Big Data systems allow collecting massive datasets to feed the data hungry deep learning. Labelling these ever-bigger datasets is increasingly challenging and label errors affect even highly curated sets. This makes robustness to label noise a critical property for weakly-supervised classifiers. The related works on resilient deep networks...

Effect of test setup on the fiber-to-mortar pull-out response in TRM composites: Experimental and analytical modeling

Textile-reinforced mortars (TRM) have recently received significant attention for the externally bonded reinforcement (EBR) of masonry and reinforced concrete structures. The fiber-to-mortar bond, the TRM-to-substrate bond, and the mechanical properties of the TRM constituents have a fundamental role in the performance of this strengthening...