论文标题
解释神经网络中的偏见：窥视代表性相似
Interpreting Bias in the Neural Networks: A Peek Into Representational Similarity
论文作者
论文摘要
对标准图像分类数据集训练的神经网络显示出对数据集偏差的耐药性。有必要理解可能与偏见的数据相对应的行为目标函数。但是，当对具有偏见的数据集训练时，几乎没有研究目标函数及其代表性结构的研究。 在本文中，我们研究了使用各种目标函数对基于偏差的数据训练的基于卷积的神经网络（例如，重新NET）的性能和内部代表性结构。我们使用集中的内核比对（CKA）专门研究表示形式的相似性，以实现不同的目标函数（概率和基于利润率的函数），并对所选的函数进行了全面的分析。 根据我们的发现，以负log似然$ $（\ MATHCAL {l} _ {nll}）$和SOFTMAX CROSS-ENTROPY（$ \ MATHCAL {L} _ {SCE} $）获得的重新NET表示表示，因为损失功能同样有能力在偏见数据上产生更好的性能和良好的表现。我们注意到，如果没有神经网络层之间的渐进代表性相似，则表现较不太可能。
Neural networks trained on standard image classification data sets are shown to be less resistant to data set bias. It is necessary to comprehend the behavior objective function that might correspond to superior performance for data with biases. However, there is little research on the selection of the objective function and its representational structure when trained on data set with biases. In this paper, we investigate the performance and internal representational structure of convolution-based neural networks (e.g., ResNets) trained on biased data using various objective functions. We specifically study similarities in representations, using Centered Kernel Alignment (CKA), for different objective functions (probabilistic and margin-based) and offer a comprehensive analysis of the chosen ones. According to our findings, ResNets representations obtained with Negative Log Likelihood $(\mathcal{L}_{NLL})$ and Softmax Cross-Entropy ($\mathcal{L}_{SCE}$) as loss functions are equally capable of producing better performance and fine representations on biased data. We note that without progressive representational similarities among the layers of a neural network, the performance is less likely to be robust.
