Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and face recognition, classification of large volumes of web data, and finance. The bottleneck is that neural network training involves iterative gradient descent and is extremely comp...

Most of the current methods of surface characterization provide only measures, parameters and patterns of the data without any prediction of useful information or recommendations for the improvement of surface quality in ultra-precision diamond turning. In this paper, a framework of a knowledge-based system (KBS) is proposed for predictive characterization of surface generation in ultra-precisi...

Fluorescence detectors are useful for various applications in biomedicine e.g. for pH-sensing or single-cell detection. Commonly conventional macroscopic optical systems are used for such applications. Planar integrated free space optical systems (PIFSO) offer the advantages of compact efficiently integrated systems and good accuracy in the terms of alignment and fabrication. Segmented flow sys...