Kristinn R. Thórisson

Kristinn R. Thórisson
Reykjavik University · School of Computer Science

Ph.D. MIT Media Lab

About

129
Publications
38,292
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,792
Citations
Citations since 2017
27 Research Items
687 Citations
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120
Additional affiliations
December 2009 - present
Icelandic Institute for Intelligent Machines
Icelandic Institute for Intelligent Machines
Position
  • Manager
August 2004 - present
Reykjavik University
Position
  • Professor (Associate)
August 2004 - February 2017
Reykjavik University
Position
  • Professor (Full)

Publications

Publications (129)
Chapter
Full-text available
The development of artificial intelligence (AI) systems has to date been largely one of man-ual labor. This constructionist approach to AI has resulted in systems with limited-domain application and severe performance brittleness. No AI architecture to date incorporates, in a single system, the many features that make natural intelligence general-p...
Conference Paper
Full-text available
The concept of understanding is commonly used in everyday communications , and seems to lie at the heart of human intelligence. However, no concrete theory of understanding has been fielded as of yet in artificial intelligence (AI), and references on this subject are far from abundant in the research literature. We contend that the ability of an ar...
Conference Paper
Full-text available
Research into the capability of recursive self-improvement typically only considers pairs of \(\langle \)agent, self-modification candidate\(\rangle \), and asks whether the agent can determine/prove if the self-modification is beneficial and safe. But this leaves out the much more important question of how to come up with a potential self-modifica...
Conference Paper
Full-text available
Dependable cyber-physical systems strive to deliver anticipative, multi-objective performance anytime, facing deluges of inputs with varying and limited resources. This is even more challenging for life-long learning rational agents as they also have to contend with the varying and growing know-how accumulated from experience. These issues are of c...
Conference Paper
Full-text available
Many existing AGI architectures are based on the assumption of infi-nite computational resources, as researchers ignore the fact that real-world tasks have time limits, and managing these is a key part of the role of intelligence. In the domain of intelligent systems the management of system resources is typi-cally called "attention". Attention mec...
Article
Full-text available
Auditing is a field of expertise often mentioned as being ripe for automation using artificial intelligence methods at all levels of operations. Primarily, the application of artificial intelligence (AI) in the auditing profession is done by and for large organizations, leveraging large datasets. While AI approaches for big data are continually imp...
Article
Full-text available
A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in its perception-cognition information processing st...
Chapter
Full-text available
Tasks are of primary importance for artificial intelligence (AI), yet no theory about their characteristics exists. The kind of task theory we envision is one that allows an objective comparison of tasks, based on measurable physical properties, and that can serve as a foundation for studying, evaluating, and comparing learning controllers of vario...
Chapter
Full-text available
Without a concrete measure of the “complicatedness” of tasks that artificial agents can reliably perform, assessing progress in AI is difficult. Only by providing evidence of progress towards more complicated tasks can developers aiming for general machine intelligence (GMI) ascertain their progress towards that goal. No such measure for this exist...
Chapter
Full-text available
Any machine targeted for human-level intelligence must be able to autonomously use its prior experience in novel situations, unforeseen by its designers. Such knowledge transfer capabilities are usually investigated under an assumption that a learner receives training in a source task and is subsequently tested on another similar target task. Howev...
Preprint
Full-text available
A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in its perception-cognition information stack. The mo...
Article
Full-text available
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / symbolic AI systems leveraging, for example, reasoning and knowledge graphs, is gaining popularity, we find there remains a need for both a clear definition of knowledge and...
Preprint
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / symbolic AI systems leveraging, for example, reasoning and knowledge graphs, is gaining popularity, we find there remains a need for both a clear definition of knowledge and...
Conference Paper
Full-text available
The knowledge that a natural learner creates based on its experience of any new situation is likely to be both partial and incorrect. To improve such knowledge with increased experience , cognitive processes must bring already-acquired knowledge towards making sense of new situations and update it with new evidence, cumulatively. For the initial cr...
Chapter
Full-text available
Autonomous knowledge transfer from a known task to a new one requires discovering task similarities and knowledge generalization without the help of a designer or teacher. How transfer mechanisms in such learning may work is still an open question. Transfer of knowledge makes most sense for learners for whom novelty is regular (other things being e...
Chapter
Full-text available
While several tools exist for training and evaluating narrow machine learning (ML) algorithms, their design generally does not follow a particular or explicit evaluation methodology or theory. Inversely so for more general learners, where many evaluation methodologies and frameworks have been suggested, but few specific tools exist. In this paper w...
Chapter
The complex socio-technological debate underlying safety-critical and ethically relevant issues pertaining to AI development and deployment extends across heterogeneous research subfields and involves in part conflicting positions. In this context, it seems expedient to generate a minimalistic joint transdisciplinary basis disambiguating the refere...
Conference Paper
Full-text available
While several tools for training and evaluating narrow machine learning (ML) algorithms exist, their design generally does not follow a particular or explicit evaluation methodology or theory. Inversely so for more general learners, where many evaluation methodologies and frameworks have been suggested but few if any specific tools exist. In this p...
Conference Paper
Full-text available
An important feature of human learning is the ability to continuously accept new information and unify it with existing knowledge, a process that proceeds largely automatically and without catastrophic side-effects. A generally intelligent machine (AGI) should be able to learn a wide range of tasks in a variety of environments. Knowledge acquisitio...
Chapter
Full-text available
An important feature of human learning is the ability to continuously accept new information and unify it with existing knowledge, a process that proceeds largely automatically and without catastrophic side-effects. A generally intelligent machine (AGI) should be able to learn a wide range of tasks in a variety of environments. Knowledge acquisitio...
Conference Paper
Full-text available
In the quest for artificial general intelligence (AGI), questions remain about what kinds of representations are needed for the kind of flexibility called for by complex environments like the physical world. A capacity for continued learning of many domains has yet to be realized, and proposals for how to achieve general performance improvement thr...
Conference Paper
Full-text available
A generally intelligent machine (AGI) should be able to learn a wide range of tasks. Knowledge acquisition in complex and dynamic task-environments cannot happen all-at-once, and AGI-aspiring systems must thus be capable of cumulative learning: efficiently making use of existing knowledge during learning, supporting increases in the scope of abilit...
Chapter
Full-text available
A generally intelligent machine (AGI) should be able to learn a wide range of tasks. Knowledge acquisition in complex and dynamic task-environments cannot happen all-at-once, and AGI-aspiring systems must thus be capable of cumulative learning: efficiently making use of existing knowledge during learning, supporting increases in the scope of abilit...
Chapter
In the quest for artificial general intelligence (AGI), questions remain about what kinds of representations are needed for the kind of flexibility called for by complex environments like the physical world. A capacity for continued learning of many domains has yet to be realized, and proposals for how to achieve general performance improvement thr...
Conference Paper
Full-text available
While many evaluation procedures have been proposed in past research for artificial general intelligence (AGI), few take the time to carefully list the (minimum, general) requirements that an AGI-aspiring (cognitive) control architecture is intended to eventually meet. Such requirements could guide the design process and help evaluate the potential...
Conference Paper
Full-text available
We consider the role of reasoning in a resource-limited controller that explicitly and continuously models its environment, and uses these models as a basis for its prediction and action. Several important features of such cumulative modeling are identified, with an emphasis on how abduction and deduction can be used to continuously prune and refin...
Article
Full-text available
We report on a series of new platforms and events dealing with AI evaluation that may change the way in which AI systems are compared and their progress is measured. The introduction of a more diverse and challenging set of tasks in these platforms can feed AI research in the years to come, shaping the notion of success and the directions of the fi...
Conference Paper
Full-text available
Artificial intelligence (AI) and machine learning (ML) research has traditionally focused most energy on constructing systems that can learn from data and/or environment interactions. This paper considers the parallel science of teaching: Artificial Pedagogy (AP). Teaching provides us with a method—aside from programming—for imparting our knowledge...
Conference Paper
Full-text available
The concept of “common sense” (“commonsense”) has had a visible role in the history of artificial intelligence (AI), primarily in the context of reasoning and what’s been referred to as “symbolic knowledge representation.” Much of the research on this topic has claimed to target general knowledge of the kind needed to ‘understand’ the world, storie...
Conference Paper
Full-text available
While evaluation of specialized tools can be restricted to the task they were designed to perform, evaluation of more general abilities and adaptation requires testing across a large range of tasks. To be helpful in the development of general AI systems, tests should not just evaluate performance at a certain point in time, but also facilitate the...
Conference Paper
Full-text available
The concept of “task” is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical foundations allow thorough evaluation of designs by methodical manipulation of well understood parameters wit...
Conference Paper
Full-text available
The concept of understanding is commonly used in everyday communications , and seems to lie at the heart of human intelligence. However, no concrete theory of understanding has been fielded as of yet in artificial intelligence (AI), and references on this subject are far from abundant in the research literature. We contend that the ability of an ar...
Article
Full-text available
The concept of “task” is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical foundations allow thorough evaluation of designs by methodical ma- nipulation of well understood parameters w...
Conference Paper
Full-text available
Evaluation of artificial intelligence (AI) systems is a prerequisite for comparing them on the many dimensions they are intended to perform on. Design of task-environments for this purpose is often ad-hoc, focusing on some limited aspects of the systems under evaluation. Testing on a wide range of tasks and environments would better facilitate comp...
Conference Paper
Full-text available
Out of fear that artificial general intelligence (AGI) might pose a future risk to human existence, some have suggested slowing or stopping AGI research, to allow time for theoretical work to guarantee its safety. Since an AGI system will necessarily be a complex closed-loop learning controller that lives and works in semi-stochastic environments,...
Patent
Full-text available
A data construct called a semcard is a semantic (meaning-based) software object including semantic meta-tags and meta-data that describes a target object or thing. A target object can be any type of digital or physical entity or identifier, or it can be tacit knowledge, such as ideas, concepts, processes or other data existing in a user's mind, pro...
Patent
Full-text available
Among other disclosure, a knowledge network and semcards enabling intelligent matching of offers and requests, involving all types of information and knowledge, including information such as classified ads, data about products and services, or knowledge, expertise, ideas, suggestions, opinions, and other forms of tacit knowledge is described.
Conference Paper
Full-text available
A significant problem facing researchers in reinforcement learning, and particularly in multi-objective learning, is the dearth of good benchmarks. In this paper, we present a method and software tool enabling the creation of random problem instances, including multi-objective learning problems, with specific structural properties. This tool, calle...
Conference Paper
Full-text available
We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forward and inverse models are initially learned through active interaction with the environment, and then enhanced and finessed by observing expert teachers. While a single i...
Conference Paper
Full-text available
Four principal features of autonomous control systems are left both unaddressed and unaddressable by present-day engineering methodologies: (1) The ability to operate effectively in environments that are only partially known at design time; (2) A level of generality that allows a system to reassess and redefine the fulfillment of its mission in lig...
Conference Paper
Full-text available
Humans and other animals are often touted as examples of systems that possess general intelligence. However, rarely if ever do they achieve high levels of intelligence and autonomy on their own: they are raised by parents and caregivers in a society with peers and seniors, who serve as teachers and examples. Current methods for developing artificia...
Conference Paper
Full-text available
An important part of human intelligence is the ability to use language. Humans learn how to use language in a society of language users, which is probably the most effective way to learn a language from the ground up. Principles that might allow an artificial agents to learn language this way are not known at present. Here we present a framework wh...
Article
Full-text available
In the domain of intelligent systems the management of system resources is typically called “attention”. Attention mechanisms exist because even environments of moderate complexity are a source of vastly more information than available cognitive resources of any known intelligence can handle. Cognitive resource management has not been of much conce...
Article
Full-text available
Four principal features of autonomous control systems are left both unaddressed and unaddressable by present-day engineering methodologies: 1. The ability to operate effectively in environments that are only partially known beforehand at design time;; 2. A level of generality that allows a system to re-assess and re-define the fulfillment of its mi...
Conference Paper
Full-text available
In this paper we consider the issue of endowing an AGI system with decision-making capabilities for operation in real-world environments or those of comparable complexity. While action-selection is a critical function of any AGI system operating in the real-world, very few applicable theories or methodologies exist to support such functionality, wh...
Conference Paper
Full-text available
Resource-boundedness must be carefully considered when designing and implementing artificial general intelligence (AGI) algorithms and architectures that have to deal with the real world. But not only must resources be represented explicitly throughout its design, an agent must also take into account their usage and the associated costs during reas...
Conference Paper
Full-text available
Systems intended to operate in dynamic, complex environments --- without intervention from their designers or significant amounts of domain-dependent information provided at design time --- must be equipped with a sufficient level of existential autonomy. This feature of naturally intelligent systems has largely been missing from cognitive architec...
Article
We present a cognitive architecture whose main constituents are allowed to grow through a situated experience in the world. Such an architectural growth is bootstrapped from a minimal initial knowledge and the architecture itself is built around the biologically-inspired notion of internal models. The key idea, supported by findings in cognitive ne...
Conference Paper
Full-text available
A key goal in designing an artificial intelligence capable of performing complex tasks is a mechanism that allows it to efficiently choose appropriate and relevant actions in a variety of situations and contexts. Nowhere is this more obvious than in the case of building a general intelligence, where the contextual choice and application of actions...
Chapter
The development of artificial intelligence (AI) systems has to date taken largely a constructionist approach, with manual programming playing a central role. After half a century of AI research, enormous gaps persist between artificial and natural intelligence. The differences in capabilities are readily apparent on virtually every scale we might w...
Conference Paper
Full-text available
Much of present AI research is based on the assumption of computational systems with infinite resources, an assumption that is either explicitly stated or implicit in the work as researchers ignore the fact that most real-world tasks must be finished within certain time limits, and it is the role of intelligence to effectively deal with such limita...
Article
Full-text available
One of the original goals of artificial intelligence (AI) research was to create machines with very general cognitive capabilities and a relatively high level of autonomy. It has taken the field longer than many had expected to achieve even a fraction of this goal; the community has focused on building specific, targeted cognitive processes in isol...
Article
Full-text available
This chapter discusses hierarchically organised actions in communication. One essential, but often overlooked, feature of natural dialogue is turn taking. More recently, turn taking has become an issue in robot and virtual human research as researchers aim to make these systems more fluent and dynamic when interacting naturally with humans. The mos...
Conference Paper
Full-text available
We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forward and inverse models are initially learned through active interaction with the environment, and then enhanced and finessed by observing expert teachers. While a single i...
Book
This book constitutes the refereed proceedings of the 11th International Conference on Intelligent Virtual Agents, IVA 2011, held in Reykjavik, Island, in September 2011. The 18 revised full papers and 27 revised short papers presented together with 25 poster papers were carefully reviewed and selected from 91 submissions. The papers are organized...
Article
Full-text available
A number of present-day problems act to hold back progress in the field of artificial intelligence (A.I.), both theoretical and pragmatic. Among the most serious pragmatic issues has to do with integration and large-scale systems construction, as much recent work on humanoids and interactive robots has
Conference Paper
Full-text available
Many dialogue systems have been built over the years that address some subset of the many complex factors that shape the behavior of participants in a face-to-face conversation. The Ymir Turntaking Model (YTTM) is a broad computational model of conversational skills that has been in development for over a decade, continuously growing in the number...
Article
Full-text available
Multimodal natural behavior of humans presents a complex yet highly coordinated set of interacting processes. Providing robots with such interactive skills is a challenging and worthy goal and numerous such efforts are currently underway; evaluating the progress in this direction, however, continues to be a challenge. General methods for measuring...
Article
Full-text available
A semantically-linked web of electronic information – the Semantic Web – promises numerous benefits including increased precision in automated information sorting, searching, organizing and summarizing. Realizing this requires significantly more reliable meta-information than is readily available today. It also requires a better way to represent in...
Conference Paper
Full-text available
The Semantic Web promises increased precision in automated information sorting, searching, organizing and summarizing. Realizing this requires significantly more reliable meta-information than is readily available for basic human-readable data types today. Relying solely on hand-crafted ontologies and annotation, or solely on artificial intelligenc...
Conference Paper
Full-text available
Several challenges remain in the effort to build software capable of conducting realtime dialogue with people. Part of the problem has been a lack of realtime flexibility, especially with regards to turntaking. We have built a system that can adapt its turntaking behavior in natural dialogue, learning to minimize unwanted interruptions and “awkward...
Conference Paper
Full-text available
One of the many benefits of agent-based modeling is the ability to develop modules in parallel, with teams focusing on isolated modules with well-defined interfaces. This also presents a challenge, however: Integrating a system with a large number of modules with complex interactions, developed by many people, is a significant challenge. Constructi...
Article
Full-text available
We have developed the Cognitive Map robot architecture that minimizes the amount of rewriting of existing legacy software for integration. The Cognitive Map can be thought of as a centralized information space for connected components to contribute both internal and environmental state information. We leverage several successfully proven concepts s...
Conference Paper
Full-text available
The complexity of advanced robot vision systems calls for an architectural framework with great flexibility with regards to sensory, hardware, processing, and communications requirements. We are currently developing a system that uses time-of-flight and a regular video stream for mobile ro bot vision applications. We present an architectural framew...
Article
Full-text available
The general intelligence of any autonomous system must in large part be measured by its ability to automatically learn new skills and integrate these with prior skills. Cognitive architectures addressing these topics are few and far between – possibly because of their difficulty. We argue that architectures capable of diverse skill acquisition and...
Article
Full-text available
Architectures for controlling communicative humanoids have been many and varied. Planning systems for multimodal behavior still require significant efforts to design and implement; this could be alleviated to some extent through the use of a common platform. In this paper we outline an approach to multimodal action generation following the SAIBA fr...
Conference Paper
Full-text available
Lacking an operational definition of autonomy has considerably weakened the concept's impact in systems engineering. Most current "autonomous" systems are built to operate in conditions more or less fully described a priori, which is insufficient for achieving highly autonomous systems that adapt efficiently to unforeseen situations. In an effort t...
Conference Paper
Full-text available
Certain necessary features of general intelligence are more system-wide than others; features such as attention, learning and temporal grounding are transversal in that they seem to affect a significant subset of all mental operation. We argue that such transversal features unavoidably impose fundamental constraints on the kinds of architectures an...