Self-Organization of Spatio-Temporal Visual Receptive Fields
スポンサーリンク
概要
- 論文の詳細を見る
A self-organizing neural network model of spatio-temporal visual receptive fields is proposed. It consists of a one-layer linear learning network with multiple temporal input channels, and each temporal channel has different impulse response. Every weight of the learning network is modified according to a Hebb-type learning algorithm proposed by Sanger. It is shown by simulation studies that various types of spatio-temporal receptive fields are self-organized by the network with random noise inputs. Some of then have similar response characteristics to X-and Y-type cells found in mammalian retina. The properties of receptive fields obtained by the network are analyzed theoretically. It is shown that only circularly symmetric receptive fields change their spatio-temporal characteristics depending on the bias of inputs. In particular, when the inputs are non-zero mean, the temporal properties of center-surround type receptive fields become heterogeneous and alter depending on the positions in the receptive fields.
- 社団法人電子情報通信学会の論文
- 1996-07-25
著者
-
TAKAHASHI Tomokazu
Graduate School of Information Science, Nagoya University
-
Takahashi Takashi
Graduate School Of Information Science Nagoya University
-
TAKAHASHI Takashi
Doctoral Program in Engineering, University of Tsukuba
-
HIRAI Yuzo
Institute of Information Sciences and Electronics, University of Tsukuba
-
Hirai Yuzo
Institute Of Information Sciences And Electronics University Of Tsukuba
関連論文
- A Novel Nuclear Export Inhibitor JBIR-02, a New Piericidin Discovered from Streptomyces sp. ML55
- New Aureothin Derivative, Alloaureothin, from Streptomyces sp. MM23
- Combining Three Different Types of Local Features for Generic Object Recognition(International Session 1)
- P-523 SELECTIVITY OF BEAUVERIOLIDE ANALOGS, ACAT INHIBITORS, TO THE ISOZYMES
- Generation of Training Data by Degradation Models for Traffic Sign Symbol Recognition(Image Recognition and Understanding)
- Appearance Manifold with Covariance Matrix for 3-D Object Recognition(CV)
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY(International Workshop on Advanced Image Technology 2007)
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY
- Human Spine Posture Estimation from 2D Frontal and Lateral Views Using 3D Physically Accurate Spine Model (ME and Human Body) (Machine Vision Applications)
- Human Spine Posture Estimation from 2D Frontal and Lateral Views Using 3D Physically Accurate Spine Model
- Self-Organization of Spatio-Temporal Visual Receptive Fields
- Microsatellite markers reveal high allelic variation in natural populations of Cryptomeria japonica near refugial areas of the last glacial period
- Face recognition based on virtual frontal view generation using LVTM with local patches clustering (パターン認識・メディア理解)
- Face recognition based on virtual frontal view generation using LVTM with local patches clustering
- Face recognition based on virtual frontal view generation using LVTM with local patches clustering