The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametric forms of nonlinear activation functions. The nonlinear forms proposed for performing the functional representation are associated with a new class of parametric neural transfer functions called rectified power sigmoid units. This class is constructed to integrate both advantages of sigmoid and rectified linear unit functions, in addition with rejecting the drawbacks of these functions. Moreover, the analytic form of this new neural class involves scale, shift and shape parameters so as to obtain a wide range of activation shapes, including the standard rectified linear unit as a limit case. Parameters of this neural transfer class are considered as learnable for the sake of discovering the complex shapes that can contribute in solving machine learning issues. Performance achieved by the joint learning of convolutional and rectified power sigmoid learnable parameters are shown outstanding in both shallow and deep learning frameworks. This class opens new prospects with respect to machine learning in the sense that learnable parameters are not only attached to linear transformations, but also to suitable nonlinear operators.
翻译:本文提议在一种双重模式中体现功能,在这种模式中,学习涉及线性进化权重和非线性激活功能的参数形式。为履行功能代表而提出的非线性形式与被称为纠正电流类模件的新型准神经转移功能有关。这一类的构建是为了结合硅状和纠正线性单位功能的优势,同时拒绝这些功能的缺陷。此外,这一新神经类的分析性形式涉及规模、转变和形状参数,以便获得范围广泛的激活形状,包括标准校正线性单元作为限制情况。这一神经神经转移类别的参数被视为可以学习,以便发现有助于解决机器学习问题的复杂形状。通过联合学习富饶和修正电流性类可学习参数,在浅深层学习框架中都表现出突出的成绩。这一类为机器学习开辟了新的前景,因为可学习的参数不仅附在线性变换中,而且也附在适当的非线性操作者身上。