Refining Neural Network Interpretability through Activation Modification

This research focuses on the problem of how to design real post-hoc modifiable Deep Neural Networks (DNNs) that can achieve or exceed state-of-the-art performance while also providing increased transparency that can help in understanding how predictions made by DNNs were reached. Existing techniques for interpretability are mostly concentrated on inspecting neuron activations as is. Here, we study controlled neuron activation adjustments during inference and examine whether these adjustments can help improve the explainable aspect and generalization of Fully Connected Neural Networks (FCNNs) without retraining. The study introduces three activation method adaptation strategies. All of them introduce a systematic adjustment of neuron activations according to individual activation magnitude, which tends to make the latent feature representation more significant in the inference phase. Experimental results show that the improvement of classification accuracies can be significant on misclassified samples as well as on overall model performance, achieving up to 14% improvements without retraining.