Unsupervised Learning of Biologically Plausible Object Recognition Strategies

Recent psychological and neurological evidence suggests that biological object recognition is a process of matching sensed images to stored iconic memories. This paper presents a partial implementation of our interpretation of Kosslyn's biological vision model, with a control system added to it. We then show how reinforcement learning can be used to control and optimize recognition in an unsupervised learning mode, where the result of image matching is used as the reward signal to optimize earlier stages of processing.

• Type: Conference
• Year: 2000
• Where: BMCV
• Authors: Bruce A. Draper, Kyungim Baek
• Keywords: Biological Object Recognition, BMCV 2000, Computer Vision, Kosslyn's Biological Vision, Unsupervised Learning Mode