Recognition of Hand Written Patterns by Rotation-Invariant Neocognitron

A rotation-invariant neocognitron, which has been recently proposed by authors, is trained by using hand-written numerical patterns provided by ETL-1 database. A new learning algorithm, "auto-generating algorithm", is proposed and the learning time is reduced. The model can recognize realistic hand-written patterns. It is also shown that the model is completely robust for rotations of hand-written patterns.

• Type: Conference
• Year: 1998
• Where: ICONIP
• Authors: Shunji Satoh, Jousuke Kuroiwa, Hirotomo Aso, Shogo Miyake
• Keywords: Hand-written Numerical Patterns, Hand-written Patterns, ICONIP 1998, ICONIP 2007, Realistic Hand-written Patterns