Skip to search formSkip to main content
You are currently offline. Some features of the site may not work correctly.

Information geometry

Information geometry is a branch of mathematics that applies the techniques of differential geometry to the field of probability theory. This is done… Expand
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2016
Highly Cited
2016
We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
Is this relevant?
Highly Cited
2016
Highly Cited
2016
This is the first comprehensive book on information geometry, written by the founder of the field. It begins with an elementary… Expand
Is this relevant?
Highly Cited
2015
Highly Cited
2015
We prove the equivalence of two online learning algorithms: 1) mirror descent and 2) natural gradient descent. Both mirror… Expand
  • table I
  • table II
  • table III
Is this relevant?
Highly Cited
2012
Highly Cited
2012
  • F. Opitz
  • 9th European Radar Conference
  • 2012
  • Corpus ID: 40396538
Information geometry is a new mathematical discipline which applies the methodology of differential geometry to statistics… Expand
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
Highly Cited
2010
Highly Cited
2010
Measures of divergence between two points play a key role in many engineering problems. One such measure is a distance function… Expand
Is this relevant?
Highly Cited
2008
Highly Cited
2008
This paper presents natural evolution strategies (NES), a novel algorithm for performing real-valued dasiablack boxpsila function… Expand
  • figure 1
  • figure 2
  • figure 3
  • table 1
  • figure 4
Is this relevant?
Highly Cited
2001
Highly Cited
2001
  • S. Amari
  • IEEE Trans. Inf. Theory
  • 2001
  • Corpus ID: 15815548
An exponential family or mixture family of probability distributions has a natural hierarchical structure. This paper gives an… Expand
  • figure 1
  • figure 2
Is this relevant?
Highly Cited
2000
Highly Cited
2000
 
Is this relevant?
Highly Cited
1997
Highly Cited
1997
There are two major approaches for blind separation: maximum entropy (ME) and minimum mutual information (MMI). Both can be… Expand
Is this relevant?
Highly Cited
1995
Highly Cited
1995
  • S. Amari
  • Neural Networks
  • 1995
  • Corpus ID: 18487371
Abstract To realize an input-output relation given by noise-contaminated examples, it is effective to use a stochastic model of… Expand
Is this relevant?