InterpNET: Neural Introspection for Interpretable Deep Learning
It addresses the need for interpretable AI in domains like image classification, though it is incremental as it builds on existing architectures.
The paper tackles the problem of deep neural networks lacking interpretability by introducing InterpNET, a design paradigm that generates natural language explanations for classifications, achieving a METEOR score of 37.9 compared to the state-of-the-art 29.2 on a bird classification dataset.
Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system's inner-workings. This paper proposes a neural network design paradigm, termed InterpNET, which can be combined with any existing classification architecture to generate natural language explanations of the classifications. The success of the module relies on the assumption that the network's computation and reasoning is represented in its internal layer activations. While in principle InterpNET could be applied to any existing classification architecture, it is evaluated via an image classification and explanation task. Experiments on a CUB bird classification and explanation dataset show qualitatively and quantitatively that the model is able to generate high-quality explanations. While the current state-of-the-art METEOR score on this dataset is 29.2, InterpNET achieves a much higher METEOR score of 37.9.