Libro

Descripción

In the field of eXplainable AI (XAI), robust “blackbox” algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require innovation in the understanding of influential and, more importantly, explainable features that directly or indirectly impact the performance of predictivity. A number of methods existing in literature focus on visualization techniques but the concepts of explainability and interpretability still require rigorous definition. In view of the above needs, this book summarizes papers that focus on an interaction-based methodology–Influence score (I-score)—to screen out the noisy and non-informative variables in the images hence it nourishes an environment with explainable and interpretable features that are directly associated to feature predictivity. Text classification is a fundamental language task in Natural Language Processing. A variety of sequential models are capable of making good predictions, yet there is a lack of connection between language semantics and prediction results. This book also introduces how the proposed methods, the novel influence score (I-score), a greedy search algorithm Backward Dropping Algorithm (BDA), and an interaction-based feature engineering can help address the long-term dependencies issues in linguistics problems.