← Search

Florian Meier

2 accepted papers

2018

Approximating Real-Time Recurrent Learning with Random Kronecker Factors

NeurIPS 2018poster

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the truncation bias, which drastically limits its ability to learn…

Cited by 72SourcePDFScholar