Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning

TitleStreaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning
Publication TypeCBMM Memos
Year of Publication2016
AuthorsLiao, Q, Kawaguchi, K, Poggio, T
Date Published10/2016
Abstract

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.

arXiv

arXiv:1610.06160v1

DSpace@MIT

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

Download:  PDF icon CBMM-Memo-057.pdf
CBMM Memo No:  057

Research Area: 

CBMM Relationship: 

  • CBMM Funded