Search for: All records

While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for neural networks to be deployed in certain high-stakes human-centered applications. To address this issue, we propose a new approach for generating interpretable predictions by inferring a simple three-layer neural network with threshold activations, so that it can benefit from effective neural network training algorithms and at the same time, produce human-understandable explanations for the results. In particular, the hidden layer neurons in the proposed model are trained with floating point weights and binary output activations. The output neuron is also trainable as a threshold logic function that implements a disjunctive operation, forming the logical-OR of the first-level threshold logic functions. This neural network can be trained using state-of-the-art training methods to achieve high prediction accuracy. An important feature of the proposed architecture is that only a simple greedy algorithm is required to provide an explanation with the prediction that is human-understandable. In comparison with other explainable decision models, our proposed approach achieves more accurate predictions on a broad set of tabular data classification datasets. 

We propose a novel three-layer neural network architecture with threshold activations for tabular data classification problems. The hidden layer units correspond to trainable neurons with arbitrary weights and biases and a step activation. These neurons are logically equivalent to threshold logic functions. The output layer neuron is also a threshold function that implements a conjunction of the hidden layer threshold functions. This neural network architecture can leverage state-of-the-art network training methods to achieve high prediction accuracy, and the network is designed so that minimal human understandable explanations can be readily derived from the model. Further, we employ a sparsity-promoting regularization approach to sparsify the threshold functions to simplify them, and to sparsify the output neuron so that it only depends on a small subset of hidden layer threshold functions. Experimental results show that our approach outperforms other state-of-the-art interpretable decision models in prediction accuracy. 

We study the faithfulness of an explanation system to the underlying prediction model. We show that this can be captured by two properties, consistency and sufficiency, and introduce quantitative measures of the extent to which these hold. Interestingly, these measures depend on the test-time data distribution. For a variety of existing explanation systems, such as anchors, we analytically study these quantities. We also provide estimators and sample complexity bounds for empirically determining the faithfulness of black-box explanation systems. Finally, we experimentally validate the new properties and estimators.