By now, the average business user has been deluged with the term Artificial Intelligence so much that he or she likely knows it frequently involves machine learning for enterprise applications of Conversational AI, intelligent search, or Natural Language Generation. With the general population still captivated by the hype around deep learning, neural networks, and predictive models, it's easy to consider rules-based systems for these applications as passé, or perhaps worse, outdated approaches to the suite of natural language technologies. According to Arria NLG CTO Neil Burnett, however, nothing could be further from reality. "Using rules is a better approach than just a [pure] machine learning approach," Burnett revealed. "We still do a good amount of rules-based generation. It's a little more elaborate than you might imagine. It's kind of a rules based approach mixed in with a little bit of ML as well."

This paper presents a probabilistic extension of the well-known cellular automaton, Game of Life. In Game of Life, cells are placed in a grid and then watched as they evolve throughout subsequent generations, as dictated by the rules of the game. In our extension, called ProbLife, these rules now have probabilities associated with them. Instead of cells being either dead or alive, they are denoted by their chance to live. After presenting the rules of ProbLife and its underlying characteristics, we show a concrete implementation in ProbLog, a probabilistic logic programming system. We use this to generate different images, as a form of rule-based generative art.

Fox Business Flash top headlines are here. Check out what's clicking on FoxBusiness.com. "May you live in interesting times," goes the old Chinese curse. When it comes to economics, "interesting" usually means the sky is falling. Inflation reached seven percent at the end of 2021, a rate not seen in forty years.

To interact with humans, artificial intelligence (AI) systems must understand our social world. Within this world norms play an important role in motivating and guiding agents. However, very few computational theories for learning social norms have been proposed. There also exists a long history of debate on the distinction between what is normal (is) and what is normative (ought). Many have argued that being capable of learning both concepts and recognizing the difference is necessary for all social agents. This paper introduces and demonstrates a computational approach to learning norms from natural language text that accounts for both what is normal and what is normative. It provides a foundation for everyday people to train AI systems about social norms.

Amid questions over his leadership, Boris Johnson is expected to make an announcement to ease coronavirus restrictions in England. There will be a review of the data later, which will inform a decision whether to change measures in place under Plan B - including face masks on transport and guidance to work from home where possible. They are due to expire next week. So far, the picture looks "encouraging", the government says, as cases fall. But it says any decision will be "finely balanced".

One of the potential solutions for model interpretation is to train a surrogate model: a more transparent model that approximates the behavior of the model to be explained. Typically, classification rules or decision trees are used due to the intelligibility of their logic-based expressions. However, decision trees can grow too deep and rule sets can become too large to approximate a complex model. Unlike paths on a decision tree that must share ancestor nodes (conditions), rules are more flexible. However, the unstructured visual representation of rules makes it hard to make inferences across rules. To address these issues, we present a workflow that includes novel algorithmic and interactive solutions. First, we present Hierarchical Surrogate Rules (HSR), an algorithm that generates hierarchical rules based on user-defined parameters. We also contribute SuRE, a visual analytics (VA) system that integrates HSR and interactive surrogate rule visualizations. Particularly, we present a novel feature-aligned tree to overcome the shortcomings of existing rule visualizations. We evaluate the algorithm in terms of parameter sensitivity, time performance, and comparison with surrogate decision trees and find that it scales reasonably well and outperforms decision trees in many respects. We also evaluate the visualization and the VA system by a usability study with 24 volunteers and an observational study with 7 domain experts. Our investigation shows that the participants can use feature-aligned trees to perform non-trivial tasks with very high accuracy. We also discuss many interesting observations that can be useful for future research on designing effective rule-based VA systems.

The estimated economic cost of all fatalities due to traffic crashes in 2018 was approximately $55 billion in the United States (CDC, 2020). Such a huge cost warrants continued investigation into the contributing factors of crash fatalities and the implementation of effective countermeasures for improving traffic safety. Traditional safety studies have generally focused on identifying correlations between crashes and roadway features. Due to a lack of substantial driving behavior information in conventional historical crash datasets, these studies can seldom identify driving behaviors that contribute to crashes. Moreover, traditional studies require crash data spanning an extended period of time.

Rule-based decision models are attractive due to their interpretability. However, existing rule induction methods often results in long and consequently less interpretable set of rules. This problem can, in many cases, be attributed to the rule learner's lack of appropriately expressive vocabulary, i.e., relevant predicates. Most existing rule induction algorithms presume the availability of predicates used to represent the rules, naturally decoupling the predicate definition and the rule learning phases. In contrast, we propose the Relational Rule Network (RRN), a neural architecture that learns relational predicates that represent a linear relationship among attributes along with the rules that use them. This approach opens the door to increasing the expressiveness of induced decision models by coupling predicate learning directly with rule learning in an end to end differentiable fashion. On benchmark tasks, we show that these relational predicates are simple enough to retain interpretability, yet improve prediction accuracy and provide sets of rules that are more concise compared to state of the art rule induction algorithms.

In some domains, for instance, in medicine, the models' predictions must be interpretable. Decision trees, classification rules, and subgroup discovery are three broad categories of supervised machine-learning models presenting knowledge in the form of interpretable rules. The accuracy of these models learned from small datasets is usually low. Obtaining larger datasets is often hard to impossible. We propose a framework dubbed PRELIM to learn better rules from small data.

Unlike many valuable resources, real-time data is both abundant and growing rapidly. But it also needs to be handled with great care. That was one of the key takeaways from an online workshop produced by Science Business' Data Rules group, which explored what the rapid growth in real-time data means for artificial intelligence (AI). Real-time data is increasingly feeding machine learning systems that then adjust the algorithms they use to make decisions, such as which news item to display on your screen or which product to recommend. "With AI, especially, you want to make sure that the data that you have is consistent, replicable and also valid," noted Chris Atherton, senior research engagement officer at GÉANT, who described how his organisation transmits data captured by the European Space Agency's satellites to researchers across the world.