发明名称 |
VISUAL OBJECT RECOGNITION SYSTEM |
摘要 |
<p>A method and apparatus for automatic object or speech recognition, for example, which uses an algorithm for the unsupervised training of hierarchical feedforward neural networks to perform transform invariant visual object recognition, referred to herein as 'continuous transformation (CT) learning'. This mechanism is based on continuous synaptic enhancement of the feedforward inter-layer connection weights using an associative (such as Hebbian) learning rule during continuous transformation (e.g. translation, rotation, etc) of the (e.g. visual) stimulus.</p> |
申请公布号 |
WO2005057474(A1) |
申请公布日期 |
2005.06.23 |
申请号 |
WO2004GB05187 |
申请日期 |
2004.12.13 |
申请人 |
ISIS INNOVATION LIMITED;STRINGER, SIMON;ROLLS, EDMUND;PERRY, GAVIN |
发明人 |
STRINGER, SIMON;ROLLS, EDMUND;PERRY, GAVIN |
分类号 |
G06K9/46;G06K9/66;(IPC1-7):G06K9/66 |
主分类号 |
G06K9/46 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|