Many software systems can be tuned for multiple objectives (e.g., faster runtime, less required memory, network traffic or energy consumption, etc.). Such suffer from “disagreement” where different models have (or even opposite) insights and tactics on how to optimize a system. For configuration problems, we show that (a) model disagreement is rampant; yet (b) prior this paper, it has barely be...

UNLABELLED Prediction and classification techniques have been well studied by machine learning researchers and developed for several real-word problems. However, the level of acceptance and success of prediction models are still below expectation due to some difficulties such as the low performance of prediction models when they are applied in different environments. Such a problem has been add...

The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack interpretability, since they have millions of unexplained model parameters. In this work, we describe Network Dissection, a method that interprets networks b...

Fuzzy rule-based systems are universal approximators of non-linear functions [1] as multilayer feedforward neural networks [2]. That is, they have a high approximation ability of non-linear functions. A large number of neural and genetic learning methods have been proposed since the early 1990s [3, 4] in order to fully utilize their approximation ability. Traditionally, fuzzy rule-based systems...

This work introduces the use of Gaussian processes (GPs) for estimation and understanding crop development yield using multisensor satellite observations meteorological data. The proposed methodology combines synergistic information on canopy greenness, biomass, soil, plant water content from optical microwave sensors with atmospheric variables typically measured at stations. A composite covari...

Most of the work we do in signal processing these days is data driven. The shift from more traditional and model-driven approaches to those that are driven has also underlined importance explainability our solutions. Because most start with a number modeling assumptions, they comprehensible by very nature their construction. However, this not necessarily case when choose rely heavily on minimiz...

Abstract This Comment explores the implications of a lack tools that facilitate an explicable utilization epistemologically richer, but also more involved white-box approaches in AI. In contrast, advances explainable artificial intelligence for black-box have led to availability semi-standardized and attractive toolchains offer seemingly competitive edge over inherently interpretable models te...