Towards a scientific foundation for engineering Cognitive Systems – A European research agenda, its rationale and perspectives

Stork, Hans-Georg

doi:10.1016/j.bica.2012.04.002

Cited by 5 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The workings of a mind (and soul) have been themes for myths, religions and philosophies over the ages. In a well-informed overview, topics, which one would like to understand better, have been listed recently [3].…”

Section: Natural Cognitionmentioning

confidence: 99%

“…In the following, it will be argued that this cognitive architecture still holds much promise waiting to be explored and utilized. It is claimed that this approach allows to address the "BICA Challenge" and to deliver towards a long list of topics, which one wishes to better understand concerning natural cognition [2,3]. Subsequently, the indicated answers can be harnessed for general AI.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

Thomsen

2021

View full text Add to dashboard Cite

The Ouroboros Model has been proposed as a biologically-inspired comprehensive cognitive architecture for general intelligence, comprising natural and artificial manifestations. The approach addresses very diverse fundamental desiderata of research in natural cognition and also artificial intelligence, AI. Here, it is described how the postulated structures have met with supportive evidence over recent years. The associated hypothesized processes could remedy pressing problems plaguing many, and even the most powerful current implementations of AI, including in particular deep neural networks. Some selected recent findings from very different fields are summoned, which illustrate the status and substantiate the proposal.

show abstract

Section: Natural Cognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

Thomsen

2021

View full text Add to dashboard Cite

show abstract

“…This claim is not with no foundation, however. The research in cognitive systems itself did not completely solve the dilemma of whether a cognitive system must incarnate cognitive processes like emotion or suffice it to be effective for the targeted task [8]. Based on this epistemological principle, we can now propose a research process for Cognitive Software Engineering:…”

Section: Research Planmentioning

confidence: 99%

Cognitive Software Engineering: A Research Framework and Roadmap

Chentouf¹

2014

JSEA

View full text Add to dashboard Cite

The work of software engineers is inherently cognitive. Integral to their duties is understanding and developing several artifacts. Each one is based on a specific model and a given level of abstraction. What distinguishes Software Engineering is the logical complexity of some artifacts (especially programs), the high dependency among them, and the fact that the success of the software project also depends on the human and social factors, which characterize the engineers as individuals and as a group. The complexity of the daily tasks within a software development team motivates the investigation on the relevance of automating the software professionals' cognitive processes in order to make their work easier and more efficient. The success of this endeavor is expected to emerge as Cognitive Software Engineering. For this aim, the present article suggests a research framework and roadmap, which build on the current state of the art. Some future directions in the Cognitive Software Engineering are presented.

show abstract

“…While a detailed commentary on these methods is out of the scope of the present study, known bottlenecks of these methods (e.g. [ 26 ]) have been the applicability and generalization to novel contexts, new tasks especially in unstructured settings, and the ability to learn cumulatively through time and experience (like natural cognitive agents). We believe, while modelling causal learning and inference from the perspective of a cumulatively developing system (animal, embodied robot), it is critical to look at the loop of perception–action, learning, memory and goal-oriented reasoning in a holistic fashion.…”

Section: Introductionmentioning

confidence: 99%

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences

Bhat¹,

Mohan²,

Sandini³

et al. 2016

J. R. Soc. Interface.

View full text Add to dashboard Cite

Emerging studies indicate that several species such as corvids, apes and children solve ‘The Crow and the Pitcher’ task (from Aesop's Fables) in diverse conditions. Hidden beneath this fascinating paradigm is a fundamental question: by cumulatively interacting with different objects, how can an agent abstract the underlying cause–effect relations to predict and creatively exploit potential affordances of novel objects in the context of sought goals? Re-enacting this Aesop's Fable task on a humanoid within an open-ended ‘learning–prediction–abstraction’ loop, we address this problem and (i) present a brain-guided neural framework that emulates rapid one-shot encoding of ongoing experiences into a long-term memory and (ii) propose four task-agnostic learning rules (elimination, growth, uncertainty and status quo) that correlate predictions from remembered past experiences with the unfolding present situation to gradually abstract the underlying causal relations. Driven by the proposed architecture, the ensuing robot behaviours illustrated causal learning and anticipation similar to natural agents. Results further demonstrate that by cumulatively interacting with few objects, the predictions of the robot in case of novel objects converge close to the physical law, i.e. the Archimedes principle: this being independent of both the objects explored during learning and the order of their cumulative exploration.

show abstract

Towards a scientific foundation for engineering Cognitive Systems – A European research agenda, its rationale and perspectives

Cited by 5 publications

References 22 publications

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

Cognitive Software Engineering: A Research Framework and Roadmap

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences

Contact Info

Product

Resources

About