Commonsense reasoning at scale is a critical problem for modern cognitive systems. Large theories have millions of axioms, but only a handful are relevant for answering a given goal query. Irrelevant axioms increase the search space, overwhelming unoptimized inference engines in large theories. Therefore, methods that help in identifying useful inference paths are an essential part of large cognitive systems. In this paper, we use retrograde analysis to build a database of proof paths that lead to at least one successful proof. This database helps the inference engine identify more productive parts of the search space. A heuristic based on this approach is used to order nodes during a search. We study the efficacy of this approach on hundreds of queries from the Cyc KB. Empirical results show that this approach leads to significant reduction in inference time.

Understanding commonsense reasoning is one of the core challenges of AI. We are exploring an approach inspired by cognitive science, called analogical chaining, to create cognitive systems that can perform commonsense reasoning. Just as rules are chained in deductive systems, multiple analogies build upon each other’s inferences in analogical chaining. The cases used in analogical chaining – called common sense units – are small, to provide inferential focus and broader transfer. Importantly, such common sense units can be learned via natural language instruction, thereby increasing the ease of extending such systems. This paper describes analogical chaining, natural language instruction via microstories, and some subtleties that arise in controlling reasoning. The utility of this technique is demonstrated by performance of an implemented system on problems from the Choice of Plausible Alternatives test of commonsense causal reasoning.

Artificial intelligence can now outperform humans in a number of advanced tasks, but when it comes to pondering life's greatest mysteries, they're still just as lost as we are. Google researchers have developed a chatbot that can carry out a natural conversation with a human, even demonstrating common sense reasoning. The system can generate solutions in an IT helpdesk scenario and even weigh in on the meaning of life – but with responses like'to live forever' and'to find out what happens when we get to the planet earth,' it doesn't quite have all the answers yet. Google researchers have developed a chatbot that can carry out a natural conversation with a human, even demonstrating common sense reasoning. In one conversation, the human participant asks the machine, 'What is the purpose of life?' A stock image is pictured Machine: to find out what happens when we get to the planet earth .

Artificial Intelligence (which I'll refer to hereafter by its nickname, "AI") is the subfield of Computer Science devoted to developing programs that enable computers to display behavior that can (broadly) be characterized as intelligent.[1] Most research in AI is devoted to fairly narrow applications, such as planning or speech-to-speech translation in limited, well defined task domains. But substantial interest remains in the long-range goal of building generally intelligent, autonomous agents,[2] even if the goal of fully human-like intelligence is elusive and is seldom pursued explicitly and as such. Throughout its relatively short history, AI has been heavily influenced by logical ideas. AI has drawn on many research methodologies: the value and relative importance of logical formalisms is questioned by some leading practitioners, and has been debated in the literature from time to time.[3]

Siri: Okay, from now on I'll call you "an ambulance." Apple fixed this error shortly after its virtual assistant was first released in 2011. But a new contest shows that computers still lack the common sense required to avoid such embarrassing mix-ups. The results of the contest were presented at an academic conference in New York this week, and they provide some measure of how much work needs to be done to make computers truly intelligent. The Winograd Schema Challenge asks computers to make sense of sentences that are ambiguous but usually simple for humans to parse.

In a 1977 article, the late AI pioneer Allen Newell foresaw a time when the entire man-made world would be permeated by systems that cushioned us from dangers and increased our abilities: smart vehicles, roads, bridges, homes, offices, appliances, even clothes. Systems built around AI components will increasingly monitor financial transactions, predict physical phenomena and economic trends, control regional transportation systems, and plan military and industrial operations. Basic research on common sense reasoning, representing knowledge, perception, learning, and planning is advancing rapidly, and will lead to smarter versions of current applications and to entirely new applications. As computers become ever cheaper, smaller, and more powerful, AI capabilities will spread into nearly all industrial, governmental, and consumer applications. Moreover, AI has a long history of producing valuable spin-off technologies.

Endowing computers with common sense is one of the major long-term goals of Artificial Intelligence research. One approach to this problem is to formalize commonsense reasoning using representations based on formal logic or other formal representations. The challenges to creating such a formalization include the accumulation of large amounts of knowledge about our everyday world, the representation of this knowledge in suitable formal languages, the integration of different representations in a coherent way, and the development of reasoning methods that use these representations.

Ever since we were classmates in our AI course (CS 486) at the University of Waterloo, way back in the summer of 2010, our vision has been to solve artificial general intelligence by creating literate machines that could think, reason and communicate like humans. Understanding human language is an extremely complex task and, ultimately, the holy grail in the field of AI. In early 2014, we observed great leaps in the fields of computer vision and speech recognition and pondered the potential of Deep Learning and Reinforcement Learning to enable our mission of creating literate machines. We realized that a great opportunity lay ahead, where machines could learn to model the intelligence and decision-making capabilities of the human brain. This meant more than simple pattern matching on text, but building systems that can actually comprehend, synthesize, infer and make logical decisions like humans. So far, our team has focused on the areas of machine reading comprehension, dialogue understanding, and general (human) intelligence capabilities such as memory, common-sense reasoning, and information seeking behavior.

Microsoft has acquired Canadian startup Maluuba, a company founded by University of Waterloo grads Kaheer Suleman and Sam Pasupalak that also participated in TechCrunch's 2012 San Francisco Startup Battlefield competition. Maluuba focuses on natural language processing, in service of pursuing general artificial intelligence, or building computers that can think like people. The Montreal-based company focuses on using deep learning and reinforcement learning to increase the proficiency and effectiveness of computer-based systems that can answer questions and make decisions, and Microsoft notes in a blog post that its work will help with Microsoft's broad goal of making AI more accessible and useful to the general public. Maluuba's focus has been on improving computer systems' ability to comprehend what they're reading, to understand natural dialog between individuals and to get better at tasks like memory, common-sense reasoning and finding information when they have a gap in their own knowledge. These are huge problems to tackle, and Maluuba notes that it became "apparent" that the best way to make progress was to tap into the significant resources made available from a larger partner.