Applying Lakatos-Style Reasoning to AI Domains

Pease, Alison; Ireland, Andrew; Colton, Simon; Ramezani, Ramin; Smaill, Alan; Llano, Maria Teresa; Grov, Gudmund; Guhe, Markus

doi:10.4018/978-1-61692-014-2.ch010

Cited by 8 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Without a theoretical literature, however, computational creativity could not dignify itself as a scientific study. The workshops have featured various proposals for models of creative processes, at various levels of abstraction (Colton 2003; Machado et al 2004; Magnani, Piazza, and Dossena 2002; McCormack 2007; Pease et al 2002; Pereira and Cardoso 2002; Sosa and Gero 2003; Wiggins 2006a; Wiggins 2006b) and also various approaches to the assessment problem, outlined earlier (Colton, Pease, and Ritchie 2001; Pease, Winterstein, and Colton 2001; Ritchie 2001; Pearce and Wiggins 2007).…”

Section: Progressmentioning

confidence: 99%

Converging on the Divergent: The History (and Future) of the International Joint Workshops in Computational Creativity

2009

View full text Add to dashboard Cite

When heckled, professional comedians frequently lament that "everyone's a comedian!" It's easy to see why: professional comedians don't possess different kinds of brains from others or engage in radically different kinds of behaviors from others, and moreover, the success of their acts is predicated on others' shared ability to understand and reason about comic situations they describe. The difference between comedians and their audience is a matter not of kind, but of degree, a difference that is reflected in the vocational emphasis they place on humor.Researchers in the field of computational creativity find themselves in a similar situation. As a subdiscipline of artificial intelligence, computational creativity explores theories and practices that give rise to a phenomenon, creativity, that all intelligent systems, human or machine, can legitimately lay claim to. Who is to say that a given AI system is not creative, insofar as it solves nontrivial problems or generates useful outputs that are not hard wired into its programming? As with comedians' being funny, the difference between studying computational creativity and studying artificial intelligence is one of emphasis rather than one of kind: the field of computational creativity, as typified by a long-running series of workshops at AI-related conferences, places a vocational emphasis on creativity and attempts to draw together the commonalities of what

show abstract

Section: Progressmentioning

confidence: 99%

Converging on the Divergent: The History (and Future) of the International Joint Workshops in Computational Creativity

2009

View full text Add to dashboard Cite

show abstract

“…In such a way, the agent can explore new models and direct efforts to expand and refine its knowledge. [61][62][63]…”

Section: Seeking Examples and Counter Examplesmentioning

confidence: 99%

Neural Model-Applying Network (Neuman): A New Basis for Computational Cognition

Roth¹

2023

ACII

View full text Add to dashboard Cite

NeuMAN represents a new model for computational cognition synthesizing important results across AI, psychology, and neuroscience. NeuMAN is based on three important ideas: (1) neural mechanisms perform all requirements for intelligence without symbolic reasoning on finite sets, thus avoiding exponential matching algorithms; (2) the network reinforces hierarchical abstraction and composition for sensing and acting; and (3) the network uses learned sequences within contextual frames to make predictions, minimize reactions to expected events, and increase responsiveness to high-value information. These systems exhibit both automatic and deliberate processes. NeuMAN accords with a wide variety of findings in neural and cognitive science and will supersede symbolic reasoning as a foundation for AI and as a model of human intelligence. It will likely become the principal mechanism for engineering intelligent systems.

show abstract

“…The enduring legacy of the DReaM group and our common interests mean that in a number of these projects we continue with existing and establish new collaborations with the past and present DReaMers. For example, Alan Bundy is serving on the advisory board of my project about representation choice and AI tools, and Alison Pease is helping us with her HRL system [29] in our mathematical education project.…”

Section: Future Directionsmentioning

confidence: 99%

Human-Like Computational Reasoning: Diagrams and Other Representations

Jamnik¹

2021

Mathematical Reasoning: The History and Impact of the DReaM Group

View full text Add to dashboard Cite

In this chapter I give a personal account of my experience in Alan Bundy's DReaM group in the Department of Artificial Intelligence at the University of Edinburgh between the years of 1995 and 1998. Of course, the impact of this experience has been profound and long-lasting to this day. The culture and the nature of research work, the collaborations, the interests and the connections have endured, evolved and multiplied throughout this time. My own work in the DReaM group started by investigating human "informal" reasoning and formalising it in a diagrammatic theorem prover. After leaving Edinburgh, this work naturally evolved into combining diagrams with other representations in a uniform framework, as well as applying visual representations in other domains, such as reasoning with ontologies. But one of the fundamental questions remained unanswered, namely, how do we choose the right representation of a problem and for a particular user in the first place?1 The DReaM research environment Few factors influence a researcher's ethos regarding their work more than where and with whom they did their PhD project. I arrived to Alan Bundy's DReaM research group in the autumn of 1995, fresh from finishing a post-graduate Diploma in Computer Science at Cambridge. This was not exactly planned: I actually applied to do a PhD in the Cognitive Science Department at the University of Edinburgh. I was interested in humans, not machines. But given that I was a mathematician by my undergraduate degree and that I just finished a post-graduate degree in Computer Science, my application made it to Alan Bundy in the Department of Artificial Intelligence. I am so glad for this serendipity, because the privilege has been immeasurable.

show abstract

Applying Lakatos-Style Reasoning to AI Domains

Cited by 8 publications

References 31 publications

Converging on the Divergent: The History (and Future) of the International Joint Workshops in Computational Creativity

Converging on the Divergent: The History (and Future) of the International Joint Workshops in Computational Creativity

Neural Model-Applying Network (Neuman): A New Basis for Computational Cognition

Human-Like Computational Reasoning: Diagrams and Other Representations

Contact Info

Product

Resources

About