arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.07407cs.LGcs.NEmath.DG
收藏

GENNI:可视化等价几何的神经网络可识别性

GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability

Imperial College London(帝国理工学院);University College London(伦敦大学学院)

Daniel Lengyel, Janith Petangoda, Isak Falk, Kate Highnam, Michalis Lazarou, Arinbjörn Kolbeinsson, Marc Peter Deisenroth, Nicholas R. Jennings

摘要:

我们提出了一个有效的算法来可视化对称性的神经网络。通常,模型是相对于参数空间定义的,其中不相等的参数可以产生相同的输入-输出映射。我们提出的方法,GENNI,使我们能够有效地识别功能等效的参数,然后可视化所得到的等价类的子空间。通过这样做,我们现在能够更好地探索围绕可识别性的问题,并应用于常用或新开发的神经网络架构的优化和泛化。

英文摘要:

We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produce the same input-output map. Our proposed method, GENNI, allows us to efficiently identify parameters that are functionally equivalent and then visualise the subspace of the resulting equivalence class. By doing so, we are now able to better explore questions surrounding identifiability, with applications to optimisation and generalizability, for commonly used or newly developed neural network architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑