Spain

We describe a reasoning framework for knowledge invention and creative problem solving that can integrate and extend the knowledge level mechanism of diverse cognitive architectures (CAs). This framework exploits an extension of a Description Logic (DL) of typicality able to combine prototypical (commonsense) descriptions of concepts. It works as follows: given a goal expressed as a set of properties, in case an intelligent agent cannot find a concept in its knowledge base (KB) able to fulfill these properties, our framework is able to dynamically recombine, in a goal-oriented perspective, the concepts in the KB in order to find a suitable creative combination able to satisfy the goal. The KB of the agent is then extended via a mechanism of commonsense concept combination where the resulting combined concept represents the solution for the initial goal. Here we discuss how such framework is compliant with the general tenets of the Standard Model of Mind and can extend the knowledge level capabilities of diverse CAs.

ECAI 2020

A goal-oriented framework for knowledge invention and creative problem solving in cognitive architectures

cognitive architectures

cognitive systems

commonsense reasoning

computational creativity

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviours that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalising what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.


ICCC'20

poster

Studying lack of information through type-2 fuzzy strong negation

A Syntactic Approach for Privacy-Preserving Federated Learning

Segmented Tables: an Efficient Modeling Tool for Constraint Reasoning

Within the autonomous driving domain, there is now a  clear need and tremendous potential for hybrid solutions (e.g., integrating  semantics, learning, visual computing) towards fulfilling essential  legal and ethical responsibilities involving explainability (e.g.,  for diagnosis), human-centred AI (e.g., interaction design), and industrial  standardisation (e.g, pertaining to representation, realisation  of rules & norms). In these contexts, this highlight paper positions
 recent research from IJCAI 2019 aimed at advancing humancentred  AI principles in the backdrop of the autonomous driving  application domain. From a technical viewpoint, the highlighted research  provides a model for advancing the state of the art in reasoning
 about space and motion, combining reasoning and learning, nonmonotonic  reasoning, and computational modelling of high-level visuospatial  commonsense. In addition to demonstrating the significance  of integrated vision and semantics solutions in autonomous  driving, we also highlight open questions emphasising the need for  interdisciplinary mixed-methods research –involving AI, Psychology,  HCI– to better appreciate the complexity and spectrum of varied
 human-centred challenges in diverse naturalistic driving situations.

Driven by Commonsense: On the Role of Human-Centred Visual Explainability for Autonomous Vehicles

The Winograd Schema Challenge (WSC) was proposed  by Levesque et al. in 2011 as a new test in Artificial Intelligence (AI)  and possibly as an alternative to the Turing test. WSC is a complex
 coreference resolution task which requires applying knowledge on  commonsense reasoning. It is an easy task for humans but it still remains  an unsolved challenge for computers. There are two categories  of proposed approaches for tackling the WSC. The first encompasses  techniques based on formalized Knowledge Representation and Reasoning  (KRR), while the second entails Machine Learning (ML)  approaches. In this paper we provide a review of the state-of-theart
 approaches proposed from both categories and we outline their  strengths and weaknesses. Additionally, we discuss a recent work  which combines techniques from both categories as it seems to be a  promising and innovative approach.

Review of the Recent Techniques for Learning Commonsense Knowledge applied to the Winograd Schema Challenge

In ongoing work we reuse existing higher-order automated reasoning infrastructure for seamlessly combining and reasoning with different non-classical logics (modal, deontic, epistemic, paraconsistent, etc.), particularly suited for normative reasoning. Our work illustrates, in particular, the utilisation of the Isabelle/HOL proof assistant for the representation and formal assessment of linguistically complex ethical arguments. Our work pushes existing boundaries in knowledge representation and reasoning. We demonstrate that intuitive, formal encodings of complex ethical theories and their automation on the computer are no longer antipodes.

Normative Reasoning with Expressive Logic Combinations

This paper provides an overview of an architecture based on the principle of step-wise refinement for knowledge representation, explainable reasoning, and interactive learning, in robotics. We briefly describe the individual components of the architecture, and emphasize how the interplay between representation, reasoning, and learning, can be exploited to enable reliable and efficient decision making in dynamic domains

REBA-KRL: Refinement-based Architecture for Knowledge Representation, Explainable Reasoning, and Interactive Learning in Robotics

The problem of reasoning with context dependent knowledge has recently gained interest in the area of description logic based knowledge bases (KBs). Among the several proposals, we consider the Contextualized Knowledge Repository (CKR) framework. The CKR model has been recently extended with the capability of reasoning with global (context independent) defeasible axioms that can be overridden by local (context specific) knowledge. In CKR applications it is often useful to reason over a hierarchical organization of contexts. We highlight here our recent efforts on extending the CKR framework to allow for the representation of exception handling in the inheritance of knowledge across local contexts. We first concentrate on a limitation to a particular kind of context organization, i.e. ranked hierarchies, which allows us to simplify the definition of reasoning procedures.We then further generalize the proposal to extend the reasoning on exception handling over general contextual hierarchies.

Reasoning with Justifiable Exceptions in Contextual Hierarchies

Leo-III is an effective automated theorem prover for extensional type theory with Henkin semantics. It is based on an extensional higher-order paramodulation calculus and supports reasoning in monomorphic and rank-1 polymorphic first-order and higher-order logics. Leo-III also automates various non-classical logics, including almost every normal higher-order modal logic.

A goal-oriented framework for knowledge invention and creative problem solving in cognitive architectures

Next from ECAI 2020

Studying lack of information through type-2 fuzzy strong negation

Similar lecture

Deep Learning as Heuristic Approach for Architectural Concept Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES