Explanation module

Abstract: Zero-shot learning (ZSL) has attracted significant attention due to its capabilities of classifying new images from unseen classes. To perform the classification task for ZSL, learning visual and semantic embeddings has been the main research approach in existing literature. At the same time, generating complementary explanations to justify the classification decision has remained largely unexplored. In this paper, we propose to address a new and challenging task, namely explainable zero-shot learning (XZSL), which aims to generate visual and textual explanations to support the classification decision. To accomplish this task, we build a novel Deep Multi-modal Explanation (DME) model that incorporates a joint visual-attribute embedding module and a multi-channel explanation module in an end-to-end fashion. In contrast to existing ZSL approaches, our visual-attribute embedding is associated not only with the decision, but also with new visual and textual explanations. For visual explanations, we first capture several attribute activation maps (AAM) and then merge them into a class activation map (CAM) that visually infers which region of an image is relevant to the class. Textual explanations are generated from the multi-channel explanation module, jointly integrating three long short-term memory models (LSTMs) each of which is conditioned on a different feature representation. Additionally, we suggest that the DME model can retain explanatory consistency for similar instances and explanatory diversity for diverse instances. We conduct qualitative and quantitative experiments to assess the model for ZSL classification and explanation. Specifically, the ablation studies verify the effectiveness of the components in our model. Our results on three well-known datasets are competitive with prior approaches. More importantly, the joint training of our embedding and explanation modules demonstrates mutual performance improvements between ZSL classification and explanation. We shed more light on DME to analyze and diagnose its advantages and limitations.

Abstract: MILORD is an expert systems building tool consisting of two inference engines and an explanation module. The system allows to perform different calculi of uncertainty on an expert defined set of linguistic terms expressing uncertainty.The different calculi of uncertainty applied to the set of linguistic terms, give, as a result, a fuzzy subset that is approximated to a linguistic certainty value belonging to the set of linguistic terms. This linguistic approximation keeps closed the calculus of uncertainty. MILORD also deals with non-monotonic reasoning in the same framework of uncertainty management. Finally, an application to the diagnosis and treatment of pneumoniae IS presented.

Abstract: A device for controlling and supervising a user during performing a fitness exercise at a fitness device (electronic Fitness Trainer) comprises a controller module for selecting at least one music piece suited for executing the fitness exercise according to a training plan, for monitoring biofeedback data obtained from the user during executing the exercise, for monitoring device data obtained from the fitness device during executing the exercise and for controlling other components of the device, an explanation module for generating an explanation message, a correction module for generating a correction message, a feedback module for generating a feedback message and an input/output module for receiving biofeedback data from the user and device data from the fitness device and for outputting the explanation message, the correction message and the feedback message as well as the selected at least one music piece to the user.

Abstract: In this paper we show that, with an appropriate component-based architecture, new functionality can be added to an Intelligent Tutoring System (ITS) with minimal effort. In particular, we show that an explanation function can be added to a component-based ITS which was originally designed to support activity in a learning-by-doing environment. We support these two claims by presenting our recent efforts to extend the Java Algebra Tutor, a variant of the PAT algebra tutor, with a generic example explanation module.