Centre for Computational Neuroscience, Department of Experimental Psychology, Oxford University, South Parks Road, Oxford, OX1 3UD, England.
Exp Brain Res. 2010 Jul;204(2):255-70. doi: 10.1007/s00221-010-2309-0. Epub 2010 Jun 11.
We show that spatial continuity can enable a network to learn translation invariant representations of objects by self-organization in a hierarchical model of cortical processing in the ventral visual system. During 'continuous transformation learning', the active synapses from each overlapping transform are associatively modified onto the set of postsynaptic neurons. Because other transforms of the same object overlap with previously learned exemplars, a common set of postsynaptic neurons is activated by the new transforms, and learning of the new active inputs onto the same postsynaptic neurons is facilitated. We show that the transforms must be close for this to occur; that the temporal order of presentation of each transformed image during training is not crucial for learning to occur; that relatively large numbers of transforms can be learned; and that such continuous transformation learning can be usefully combined with temporal trace training.
我们证明，通过在腹侧视觉系统的皮层处理的分层模型中的自组织，空间连续性可以使网络学习到对象的平移不变表示。在“连续变换学习”期间，来自每个重叠变换的活动突触被联想性地修改到一组突触后神经元上。由于同一对象的其他变换与先前学习的范例重叠，因此新变换激活了一组共同的突触后神经元，并且促进了对相同突触后神经元的新活动输入的学习。我们表明，为了发生这种情况，变换必须接近；在训练期间呈现每个变换图像的时间顺序对于学习的发生并不是至关重要的；可以学习相对大量的变换；并且这种连续的变换学习可以与时间轨迹训练很好地结合使用。
