An Unsupervised Algorithm For Learning Lie Group Transformations
An Unsupervised Algorithm For Learning Lie Group Transformations
复制标题
一种用于学习李群变换的无监督算法
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
B. Olshausen
中科院分区：
文献类型：
--
作者：
Jascha Narain Sohl;Jimmy C. Wang;B. Olshausen
我们提出了几个理论贡献，允许李群适合于高维数据集。变换算子用特征基表示，将参数估计的计算复杂度降低到训练线性变换模型的计算复杂度。引入了一个特定于变换的“模糊”算子，该算子允许推理通过变换空间的平滑来逃避局部极小值。增加了对遍历流形距离的惩罚，鼓励发现稀疏，最小距离，状态之间的转换。使用这些方法对自然图像斑块上的全套仿射变换进行了学习和推理。然后对变换算子进行自然视频序列的训练。实验表明，与基于刚性平移的标准运动模型相比，学习视频变换能更好地描述帧间差异。
We present several theoretical contributions which allow Lie groups to be fit to high dimensional datasets. Transformation operators are represented in their eigen-basis, reducing the computational complexity of parameter estimation to that of training a linear transformation model. A transformation specific "blurring" operator is introduced that allows inference to escape local minima via a smoothing of the transformation space. A penalty on traversed manifold distance is added which encourages the discovery of sparse, minimal distance, transformations between states. Both learning and inference are demonstrated using these methods for the full set of affine transformations on natural image patches. Transformation operators are then trained on natural video sequences. It is shown that the learned video transformations provide a better description of inter-frame differences than the standard motion model based on rigid translation.
影响因子：
2.5
作者：
J. Victor;F. Mechler;M. A. Repucci;K. Purpura;T. Sharpee
通讯作者：
J. Victor;F. Mechler;M. A. Repucci;K. Purpura;T. Sharpee
登记。
DOI：
10.1007/978-1-4939-7647-8_1
发表时间：
2018
期刊：
Neuromethods
影响因子：
--
作者：
Joshi,AnandA
通讯作者：
Joshi,AnandA