He is currently working part-time as a senior research scientist at the Fuzzy Logic Systems Institute in Fukuoka, Japan.
[1] In 1980, Fukushima published the neocognitron,[2][3] the original deep convolutional neural network (CNN) architecture.
[5][7] In 1969 Fukushima introduced the ReLU (Rectifier Linear Unit) activation function in the context of visual feature extraction in hierarchical neural networks, which he called "analog threshold element".
[8][9] (Though the ReLU was first used by Alston Householder in 1941 as a mathematical abstraction of biological neural networks.
[1] Fukushima acted as founding president of the Japanese Neural Network Society (JNNS).