Shun'ichi Amari | |
|---|---|
甘利 俊一 | |
 Shun'ichi Amari | |
| Born | 1936 (age 88–89) |
| Alma mater | University of Tokyo |
| Known for | Information geometry Amari distance Artificial intelligence |
| Awards | IEEE Emanuel R. Piore Award (1997) Kyoto Prize (2025) |
| Scientific career | |
| Fields | Neuroscience |
| Institutions | RIKEN |
Shun'ichi Amari (甘利 俊一,Amari Shun'ichi), is a Japanese engineer and neuroscientist born in 1936 inTokyo, Japan. He was a pioneer ininformation geometry andartificial intelligence.
He majored in Mathematical Engineering in 1958 from theUniversity of Tokyo then graduated in 1963 from the Graduate School of theUniversity of Tokyo.
HisMaster of Engineering in 1960 was entitledTopological and Information-Theoretical Foundation of Diakoptics and Codiakoptics.HisDoctor of Engineering in 1963 was entitledDiakoptics of Information Spaces.
Shun'ichi Amari received several awards and is a visiting professor of various universities.
He is the author of more than 200 peer-reviewed articles.[1] He is known for developinginformation geometry. He also independently invented theHopfield network in 1972,[2] a form of self-organizedrecurrent neural network.
Amari made significant advances inartificial intelligence. In 1967, he proposed the firstdeep learningartificial neural network (ANN) using thestochastic gradient descent (SGD) algorithm. The same year, Amari and his student H. Saito reported the firstmultilayer perceptron (MLP) neural networktrained by SGD.[3] The concept ofbackpropagation was also anticipated by Amari in the 1960s.[4]
In 1972, Amari and Kaoru Nakano published the first papers on deep learningrecurrent neural networks (RNN). The same year, Amari invented theAmari–Hopfield network. The Amari network, the earliest deep learningrecurrent neural network (RNN), was first published by Amari in 1972. It was rediscovered byJohn Hopfield in 1982 as theHopfield network.[3]
He is currently holding a position of theRIKEN lab and is vice-president of Brain Science Institute, director of Brain Style Information Systems Group and team leader of Mathematical Neuroscience Laboratory.[5]
He was a winner of theIEEE Emanuel R. Piore Award (1997).[6]
