Ecole Polytechnique Federale De Lausanne

Wafa Johal

Francesco Mondada

Thibault Asselborn

Ayberk Özgür

Séverin Lemaignan

Konrad Zolna

Pierre Dillenbourg

The present invention concerns a method for an artificial neural network to confirm the recognition of handwritten characters produced by a user. The method comprising: training the artificial neural network with a training data set comprising a first set of characters; collecting handwritten characters of a second set of characters produced by the user; and analysing the collected characters of the second set of characters by using the artificial neural network to obtain a first set of probability values comprising character specific probability values for the collected characters, each character specific probability value indicating the probability that the collected character has been correctly interpreted. The analysis considers at least the manner how the collected characters are handwritten and the appearance of the collected characters to obtain the character specific probability values. The invention also relates to a corresponding data processing apparatus.

Method of handwritten character recognition confirmation

The present invention concerns a magnet-assisted ball drive. The drive comprises a ball and a drive element in contact with the ball. The drive element is arranged to be rotated around its axis of rotation to drive the ball. The ball and the drive element each comprise magnetic material such that at least one of the ball and the drive element comprises a magnet to generate a magnetic pulling force to pull the ball and the drive element against each other.

Magnet-assisted ball drive

Growing community of inventors

Randwick, Australia

Wafa Johal