论文标题
稀疏编码中的可解释词典
The Interpretable Dictionary in Sparse Coding
论文作者
论文摘要
人工神经网络（ANN），特别是深度学习网络，通常被标记为黑匣子，因为数据的内部表示不容易解释。在我们的工作中，我们说明了一个在特定的稀疏性约束下使用稀疏编码训练的ANN产生的模型比标准深度学习模型更容易解释。通过稀疏编码学到的字典可以更容易地理解，这些元素的激活产生了选择性的功能输出。我们将稀疏编码模型与对相同数据训练的等效卷积自动编码器进行比较和对比。我们的结果表明，在解释学习的稀疏编码词典以及内部激活表示方面，既有定性和定量益处。
Artificial neural networks (ANNs), specifically deep learning networks, have often been labeled as black boxes due to the fact that the internal representation of the data is not easily interpretable. In our work, we illustrate that an ANN, trained using sparse coding under specific sparsity constraints, yields a more interpretable model than the standard deep learning model. The dictionary learned by sparse coding can be more easily understood and the activations of these elements creates a selective feature output. We compare and contrast our sparse coding model with an equivalent feed forward convolutional autoencoder trained on the same data. Our results show both qualitative and quantitative benefits in the interpretation of the learned sparse coding dictionary as well as the internal activation representations.
