Amazing that @SchmidhuberAI gave this talk back in 2012, months before AlexNet paper was published.
In 2012, many things he discussed, people just considered to be funny and a joke, but the same talk now would be considered at the center of AI debate and controversy.
Full talk:
@francoisfleuret For seq2seq, to predict the output sequence at each step, the predicted token from the precious time step is fed into the decoder as input. How can that be achieved without a loop?