Laurens R. Leerink

Learn More
| We investigate the learning of de-terministic nite-state automata (DFA's) with recurrent networks with a single input neu-ron, where each input symbol is represented as a temporal pattern and strings as sequences of temporal patterns. We empirically demonstrate that obvious temporal encodings can make learning very diicult or even impossible. Based on(More)
Hydroxyapatite (HA)/titania (TiO2) composite coatings were successfully prepared in an electrolyte solution contain Ca 2+ and H2PO4 ions with added TiO2 particles, between 100 -C and 200 -C in an autoclave through a hydrothermal–electrochemical codeposited method under galvanostatic conditions. The effect of TiO2 additions on the phase composition,(More)
  • 1