Many explainable AI (XAI) techniques strive for interpretability by providing concise salient information, such as sparse linear factors. However, users either only see inaccurate global explanations, or highly-varying local explanations. We propose to provide more detailed explanations by leveraging the human cognitive capacity to accumulate knowledge by incrementally receiving more details. Focusing on linear factor explanations (factors $\times$ values = outcome), we introduce Incremental XAI to automatically partition explanations for general and atypical instances by providing Base + Incremental factors to help users read and remember more faithful explanations. Memorability is improved by reusing base factors and reducing the number of factors shown in atypical cases. In modeling, formative, and summative user studies, we evaluated the faithfulness, memorability and understandability of Incremental XAI against baseline explanation methods. This work contributes towards more usable explanation that users can better ingrain to facilitate intuitive engagement with AI.

One small molecule that helps regulate gene expression plays a big role in keeping us safe from the machinations of cancer, scientists report. In human lung cancer cells, they have shown low levels of the microRNA, miR-125a-5p, which enables the death of aberrant cells like cancer cells, correlates with high levels of the protein TIMP-1, which is already associated with a poor prognosis in patients with cancer....

With AlphaGo, DeepMind demonstrated the power of machine-learning to beat humans. Put simply, AI refers to technologies that try to replicate core human functions. Peet van Biljon, formerly of McKinsey and now one of the leading innovation specialists engaging with the topic, sums it up neatly: "It's about computers doing things ever smarter than we used to expect of machines, and ever closer to what we thought only humans could do." The resemblance to human intelligence is no coincidence, he says, as "recent advances all involve some sort of neural network, which is modelled on how we think the human brain works." At the heart of the excitement over AI is the concept of machine learning: computers working things out for themselves without being explicitly programmed to do so.