Finite State Controllers (FSCs) are an effective way to represent sequential plans compactly. By imposing appropriate conditions on transitions, FSCs can also represent generalized plans that solve a range of planning problems from a given domain. In this paper we introduce the concept of hierarchical FSCs for planning by allowing controllers to call other controllers. We show that hierarchical FSCs can represent generalized plans more compactly than individual FSCs. Moreover, our call mechanism makes it possible to generate hierarchical FSCs in a modular fashion, or even to apply recursion. We also introduce a compilation that enables a classical planner to generate hierarchical FSCs that solve challenging generalized planning problems. The compilation takes as input a set of planning problems from a given domain and outputs a single classical planning problem, whose solution corresponds to a hierarchical FSC. 1 Introduction Finite state controllers (FSCs) are a compact and effective representation commonly used in AI; prominent examples include robotics [ Brooks, 1989 ] and video-games [ Buckland, 2004] . In planning, FSCs offer two main benefits: 1) solution compactness [ B ackstr om et al., 2014 ]; and 2) the ability to represent generalized plans that solve a range of similar planning problems. This generalization capacity allows FSCs to represent solutions to arbitrarily large problems, as well as problems with partial observability and non-deterministic actions [ Bonet et al., 2010; Hu and Levesque, 2011; Srivastava et al., 2011; Hu and De Giacomo, 2013 ] .

Building on recent work on capsule networks, we propose a new, general-purpose form of "routing by agreement" that activates output capsules in a layer as a function of their net benefit to use and net cost to ignore input capsules from earlier layers. To illustrate the usefulness of our routing algorithm, we present two capsule networks that apply it in different domains: vision and language. The first network achieves new state-of-the-art accuracy of 99.1% on the smallNORB visual recognition task with fewer parameters and an order of magnitude less training than previous capsule models, and we find evidence that it learns to perform a form of "reverse graphics." The second network achieves new state-of-the-art accuracies on the root sentences of the Stanford Sentiment Treebank: 58.5% on fine-grained and 95.6% on binary labels with a single-task model that routes frozen embeddings from a pretrained transformer as capsules. In both domains, we train with the same regime. Code is available at https://github.com/glassroom/heinsen_routing along with replication instructions.

While the philosophical literature has extensively studied how decisions relate to arguments, reasons and justifications, decision theory almost entirely ignores the latter notions and rather focuses on preference and belief. In this article, we argue that decision theory can largely benefit from explicitly taking into account the stance that decision-makers take towards arguments and counter-arguments. To that end, we elaborate a formal framework aiming to integrate the role of arguments and argumentation in decision theory and decision aid. We start from a decision situation, where an individual requests decision support. In this context, we formally define, as a commendable basis for decision-aid, this individual's deliberated judgment, popularized by Rawls. We explain how models of deliberated judgment can be validated empirically. We then identify conditions upon which the existence of a valid model can be taken for granted, and analyze how these conditions can be relaxed. We then explore the significance of our proposed framework for decision aiding practice. We argue that our concept of deliberated judgment owes its normative credentials both to its normative foundations (the idea of rationality based on arguments) and to its reference to empirical reality (the stance that real, empirical individuals hold towards arguments and counter-arguments, on due reflection). We then highlight that our framework opens promising avenues for future research involving both philosophical and decision theoretic approaches, as well as empirical implementations.

Artificial intelligence – AI for those in the technological know – gets a bad rap and Anshumali (Anshu) Shrivastava came to the Lake Houston Chamber's October luncheon to clear the air and tell business leaders how AI is changing their business landscape. "The best way I can describe artificial intelligence is to use the example of self-driving cars," Shrivastava said at the Oct. 29 meeting at the Clubs of Kingwood. "When you're driving, there's lots to think about. And driving on the highway is certainly different than driving on a busy city street."

Artificial intelligence – AI for those in the technological know – gets a bad rap and Anshumali (Anshu) Shrivastava came to the Lake Houston Chamber's October luncheon to clear the air and tell business leaders how AI is changing their business landscape. "The best way I can describe artificial intelligence is to use the example of self-driving cars," Shrivastava said at the Oct. 29 meeting at the Clubs of Kingwood. "When you're driving, there's lots to think about. And driving on the highway is certainly different than driving on a busy city street."

If anybody read the word Artificial Intelligence (AI), he starts thinking that he will come to a shopping mall on his self-driven car and there a robot opens his car door. All services are automated without human presence, like greeter, house staff, and security guard. Every job is done by a robot. This perception is very much aligned for AI in near future, but are we adopting AI properly in Pakistan? Are we following ethical codes to use AI for improvement of human conditions?

MINNEAPOLIS--(BUSINESS WIRE)-- U.S. Bank (USBK) has hired technology leader Dr. Tanushree Luke to lead Artificial Intelligence (AI) efforts at the company. In this role, she will drive the continued development of the AI practice within the U.S. Bank Innovation group and AI strategies across the enterprise. This press release features multimedia. U.S. Bank has hired technology leader Dr. Tanushree Luke to lead Artificial Intelligence (AI) efforts at the company. Dr. Luke's career has spanned multiple industries and sectors.

The market is expected to reach $15.44 billion by 2024 at a CAGR of 8.30% with improvements in early disease diagnosis, finds Frost & Sullivan October 28, 2019 – With both large pharmaceutical companies and mid-sized biotechs adopting emerging technologies such as artificial intelligence and machine learning, there has been a reorientation of drug discovery and development, validation, testing, and clinical deployment. Scientific advancements such as cell and gene therapies and understanding of the microbiome, plus improvements in early disease diagnostics, are expected to drive the $9.56 billion neurodegenerative disorder (ND) therapeutics market for Alzheimer's and Parkinson's Diseases (AD/PD) toward $15.44 billion in 2024 at a compound annual growth rate (CAGR) of 8.30%. "With the alarming attrition rate of clinical pipeline for Alzheimer's and Parkinson's, and elusive success of therapies in their ability to modify disease, the future of the therapy hinges on the course of action companies take today," said Khushbu Jain, Transformational Health Industry Analyst. "As the understanding of science behind disease deepens and offers new pathways for drug development, pharma companies will have to seek additional avenues for revenue and unconventional partnerships to offer immediate solutions to patients. The most lucrative partners remain digital platform providers that can help manage the disease better, help expedite drug discovery and, ultimately, deliver on outcome-based care."

Lyft, the second largest ride-hailing service in the U.S., once helped disrupt the taxi industry. Now, the company is working hard to avoid being disrupted itself as self-driving cars turn from sci-fi into reality. According to Taggart Matthiesen, vice president of product at Lyft's Autonomous Group, the company has assigned around 400 of its engineers to work on two distinct self-driving initiatives. One is the "open platform" where Lyft connects passengers with semi-autonomous vehicles created by its partners, including Aptiv in Las Vegas and Alphabet's Waymo in Chandler, Arizona. The other is Lyft's effort to create its own self-driving systems, work that it does primarily at Level 5, its sizable lab in an unassuming office park in Palo Alto, Calif.

A prominent rights group is urging the Federal Trade Commission to take on the recruiting-technology company HireVue, arguing the firm has turned to unfair and deceptive trade practices in its use of face-scanning technology to assess job candidates' "employability." The Electronic Privacy Information Center, known as EPIC, on Wednesday filed an official complaint calling on the FTC to investigate HireVue's business practices, saying the company's use of unproven artificial-intelligence systems that scan people's faces and voices constituted a wide-scale threat to American workers. HireVue's "AI-driven assessments," which more than 100 employers have used on more than a million job candidates, use video interviews to analyze hundreds of thousands of data points related to a person's speaking voice, word selection and facial movements. The system then creates a computer-generated estimate of the candidates' skills and behaviors, including their "willingness to learn" and "personal stability." Candidates aren't told their scores, but employers can use those reports to decide whom to hire or disregard. The the Utah-based company was the subject of a Washington Post report last month, in which AI researchers criticized its technology as "profoundly disturbing" and "opaque."