Vision Science Graduate Group, University of California Berkeley, Berkeley, CA, USA.
Redwood Center for Theoretical Neuroscience, University of California Berkeley, Berkeley, CA, USA.
J Vis. 2020 Nov 2;20(12):10. doi: 10.1167/jov.20.12.10.
We investigate how the population nonlinearities resulting from lateral inhibition and thresholding in sparse coding networks influence neural response selectivity and robustness. We show that when compared to pointwise nonlinear models, such population nonlinearities improve the selectivity to a preferred stimulus and protect against adversarial perturbations of the input. These findings are predicted from the geometry of the single-neuron iso-response surface, which provides new insight into the relationship between selectivity and adversarial robustness. Inhibitory lateral connections curve the iso-response surface outward in the direction of selectivity. Since adversarial perturbations are orthogonal to the iso-response surface, adversarial attacks tend to be aligned with directions of selectivity. Consequently, the network is less easily fooled by perceptually irrelevant perturbations to the input. Together, these findings point to benefits of integrating computational principles found in biological vision systems into artificial neural networks.
我们研究了稀疏编码网络中侧向抑制和阈值产生的群体非线性如何影响神经反应的选择性和鲁棒性。我们表明，与逐点非线性模型相比，这种群体非线性可以提高对首选刺激的选择性，并防止输入受到对抗性的干扰。这些发现是从单神经元等响应面的几何形状预测的，这为选择性和对抗鲁棒性之间的关系提供了新的见解。抑制性的侧向连接使等响应面在选择性的方向上向外弯曲。由于对抗性的干扰与等响应面正交，因此对抗性攻击往往与选择性的方向一致。因此，网络不太容易受到输入的与感知无关的干扰的欺骗。总之，这些发现表明，将生物视觉系统中发现的计算原理整合到人工神经网络中是有益的。
