Unsupervised learning of spatial transformations in the absence of temporal continuity
CIMSIVP(2014)
摘要
Learning features invariant to arbitrary transformations in the data is a requirement for any recognition system, biological or artificial. Such transformations may be learned using label information or from temporal data in an unsupervised manner by exploiting continuity. This paper presents a dynamical system for learning invariances from real-world spatial patterns in an unsupervised manner and in the absence of temporal continuity. The model consists of a simple and a complex layers. Given an input, the simple layer imagines all of its variations, each with a degree of consistency, and eventually settles for the most consistent reconstruction. During this imagination, the complex layer learns the consistent variations of the same pattern as a transformation in each spatial region. Experimental results are comparable to those from supervised learning. The conditions for stability of the system are analyzed.
更多查看译文
关键词
spatial transformations,complex layer,dynamical system,learning invariances,real-world spatial patterns,simple layer,unsupervised learning,image reconstruction,computer architecture,feedforward neural networks,silicon,noise measurement,stability analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络