%0 Generic %D 2016 %T Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning %A Qianli Liao %A Kenji Kawaguchi %A Tomaso Poggio %X

We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent learning. Our proposal is simpler and more biologically-plausible. Unlike previous approaches, our technique can be applied out of the box to all learning scenarios (e.g., online learning, batch learning, fully-connected, convolutional, feedforward, recurrent and mixed — recurrent and convolutional) and compare favorably with existing approaches. We also propose Lp Normalization for normalizing by different orders of statistical moments. In particular, L1 normalization is well-performing, simple to implement, fast to compute, more biologically-plausible and thus ideal for GPU or hardware implementations.

%8 10/2016 %1

arXiv:1610.06160v1

%2

http://hdl.handle.net/1721.1/104906