Jürgen Schmidhuber (Swiss AI Lab IDSIA)
Slides available at: idsia.ch/~juergen/deeplearning2014slides.pdf
Machine learning and pattern recognition are currently being revolutionised by "Deep Learning"(DL) Neural Networks (NNs). This is of commercial interest (for example, Google spent over 400m on start-up "deepmind" co-founded by our student). My talk will summarise our work on DL since 1991. Our recurrent NNs (RNNs) were the first to win official international competitions in pattern recognition and machine learning; our team has won more such contests than any other research group or company. In particular, our RNNs represent the state of the art in connected handwriting recognition, and aspects of speech recognition. Our Deep Learners also were the first to win object detection and image segmentation contests. We also built the first artificial RNN-based agent that learns from scratch complex control based on high-dimensional vision. Time permitting, I'll also address curious/creative machines and theoretically optimal, universal, self-modifying artificial intelligences.
Thanks to Upsight for hosting and Tommy Chheng for video recording!