Last year, Microsoft Corp.'s Azure security team detected suspicious activity in the cloud computing usage of a large retailer: One of the company's administrators, who usually logs on from New York, was trying to gain entry from Romania. A hacker had broken in. Microsoft quickly alerted its customer, and the attack was foiled before the intruder got too far. Inc. and various startups are moving away from solely using older "rules-based" technology designed to respond to specific kinds of intrusion and deploying machine-learning algorithms that crunch massive amounts of data on logins, behavior and previous attacks to ferret out and stop hackers. "Machine learning is a very powerful technique for security--it's dynamic, while rules-based systems are very rigid," says Dawn Song, a professor at the University of California at Berkeley's Artificial Intelligence Research Lab. "It's a very manual intensive process to change them, whereas machine learning is automated, dynamic and you can retrain it easily."

Last year, Microsoft Corp.'s Azure security team detected suspicious activity in the cloud computing usage of a large retailer: One of the company's administrators, who usually logs on from New York, was trying to gain entry from Romania. A hacker had broken in. Microsoft quickly alerted its customer, and the attack was foiled before the intruder got too far. Microsoft, Alphabet Inc.'s Google, Amazon.com and various startups are moving away from solely using older "rules-based" technology designed to respond to specific kinds of intrusion and deploying machine-learning algorithms that crunch massive amounts of data on logins, behavior and previous attacks to ferret out and stop hackers. "Machine learning is a very powerful technique for security-it's dynamic, while rules-based systems are very rigid," says Dawn Song, a professor at the University of California at Berkeley's Artificial Intelligence Research Lab. "It's a very manual intensive process to change them, whereas machine learning is automated, dynamic and you can retrain it easily."

Last year, Microsoft Corp.'s Azure security team detected suspicious activity in the cloud computing usage of a large retailer: One of the company's administrators, who usually logs on from New York, was trying to gain entry from Romania. A hacker had broken in. Microsoft quickly alerted its customer, and the attack was foiled before the intruder got too far. Inc. and various startups are moving away from solely using older "rules-based" technology designed to respond to specific kinds of intrusion and deploying machine-learning algorithms that crunch massive amounts of data on logins, behavior and previous attacks to ferret out and stop hackers. "Machine learning is a very powerful technique for security--it's dynamic, while rules-based systems are very rigid," says Dawn Song, a professor at the University of California at Berkeley's Artificial Intelligence Research Lab. "It's a very manual intensive process to change them, whereas machine learning is automated, dynamic and you can retrain it easily."

One of the biggest news subjects in the past few years has been artificial intelligence. We have read about how Google's DeepMind beat the world's best player at Go, which is thought of as the most complex game humans have created; witnessed how IBM's Watson beat humans in a debate; and taken part in a wide-ranging discussion of how A.I. applications will replace most of today's human jobs in the years ahead. Way back in 1983, I identified A.I. as one of 20 exponential technologies that would increasingly drive economic growth for decades to come. Early rule-based A.I. applications were used by financial institutions for loan applications, but once the exponential growth of processing power reached an A.I. tipping point, and we all started using the Internet and social media, A.I. had enough power and data (the fuel of A.I.) to enable smartphones, chatbots, autonomous vehicles and far more. As I advise the leadership of many leading companies, governments and institutions around the world, I have found we all have different definitions of and understandings about A.I., machine learning and other related topics.

Last year, Microsoft Corp.'s Azure security team detected suspicious activity in the cloud computing usage of a large retailer: One of the company's administrators, who usually logs on from New York, was trying to gain entry from Romania. A hacker had broken in. Microsoft quickly alerted its customer, and the attack was foiled before the intruder got too far. Inc. and various startups are moving away from solely using older "rules-based" technology designed to respond to specific kinds of intrusion and deploying machine-learning algorithms that crunch massive amounts of data on logins, behavior and previous attacks to ferret out and stop hackers. "Machine learning is a very powerful technique for security--it's dynamic, while rules-based systems are very rigid," says Dawn Song, a professor at the University of California at Berkeley's Artificial Intelligence Research Lab. "It's a very manual intensive process to change them, whereas machine learning is automated, dynamic and you can retrain it easily."

One of the biggest news subjects in the past few years has been artificial intelligence. We have read about how Google's DeepMind beat the world's best player at Go, which is thought of as the most complex game humans have created; witnessed how IBM's Watson beat humans in a debate; and taken part in a wide-ranging discussion of how A.I. applications will replace most of today's human jobs in the years ahead. Way back in 1983, I identified A.I. as one of 20 exponential technologies that would increasingly drive economic growth for decades to come. Early rule-based A.I. applications were used by financial institutions for loan applications, but once the exponential growth of processing power reached an A.I. tipping point, and we all started using the Internet and social media, A.I. had enough power and data (the fuel of A.I.) to enable smartphones, chatbots, autonomous vehicles and far more. As I advise the leadership of many leading companies, governments and institutions around the world, I have found we all have different definitions of and understandings about A.I., machine learning and other related topics.

One of the biggest news subjects in the past few years has been artificial intelligence. We have read about how Google's DeepMind beat the world's best player at Go, which is thought of as the most complex game humans have created; witnessed how IBM's Watson beat humans in a debate; and taken part in a wide-ranging discussion of how A.I. applications will replace most of today's human jobs in the years ahead. Way back in 1983, I identified A.I. as one of 20 exponential technologies that would increasingly drive economic growth for decades to come. Early rule-based A.I. applications were used by financial institutions for loan applications, but once the exponential growth of processing power reached an A.I. tipping point, and we all started using the Internet and social media, A.I. had enough power and data (the fuel of A.I.) to enable smartphones, chatbots, autonomous vehicles and far more. As I advise the leadership of many leading companies, governments and institutions around the world, I have found we all have different definitions of and understandings about A.I., machine learning and other related topics.

This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjunctive normal form (CNF, AND-of-ORs) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy for rule simplicity. Column generation (CG) is used to efficiently search over an exponential number of candidate clauses (conjunctions or disjunctions) without the need for heuristic rule mining. This approach also bounds the gap between the selected rule set and the best possible rule set on the training data. To handle large datasets, we propose an approximate CG algorithm using randomization. Compared to three recently proposed alternatives, the CG algorithm dominates the accuracy-simplicity trade-off in 8 out of 16 datasets. When maximized for accuracy, CG is competitive with rule learners designed for this purpose, sometimes finding significantly simpler solutions that are no less accurate.

We present the Multi-value Rule Set (MRS) for interpretable classification with feature efficient presentations. Compared to rule sets built from single-value rules, MRS adopts a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than classical singlevalue rules in capturing and describing patterns in data. Our formulation also pursues a higher efficiency of feature utilization, which reduces possible cost in data collection and storage. We propose a Bayesian framework for formulating an MRS model and develop an efficient inference method for learning a maximum a posteriori, incorporating theoretically grounded bounds to iteratively reduce the search space and improve the search efficiency. Experiments on synthetic and realworld data demonstrate that MRS models have significantly smaller complexity and fewer features than baseline models while being competitive in predictive accuracy. Human evaluations show that MRS is easier to understand and use compared to other rule-based models.

We present the Multi-value Rule Set (MRS) for interpretable classification with feature efficient presentations. Compared to rule sets built from single-value rules, MRS adopts a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than classical single-value rules in capturing and describing patterns in data. Our formulation also pursues a higher efficiency of feature utilization, which reduces possible cost in data collection and storage. We propose a Bayesian framework for formulating an MRS model and develop an efficient inference method for learning a maximum a posteriori, incorporating theoretically grounded bounds to iteratively reduce the search space and improve the search efficiency. Experiments on synthetic and real-world data demonstrate that MRS models have significantly smaller complexity and fewer features than baseline models while being competitive in predictive accuracy.