Search

This report documents the program and the outcomes of Dagstuhl Seminar 17192 "Human-Like Neural-Symbolic Computing", held from May 7th to 12th, 2017. The underlying idea of Human-Like Computing is to incorporate into Computer Science aspects of how humans learn, reason and compute. Whilst recognising the relevant scientific trends in big data and deep learning, capable of achieving state-of-the-art performance in speech recognition and computer vision tasks, limited progress has been made towards understanding the principles underlying language and vision understanding. Under the assumption that neural-symbolic computing - the study of logic and connectionism as well statistical approaches - can offer new insight into this problem, the seminar brought together computer scientists, but also specialists on artificial intelligence, cognitive science, machine learning, knowledge representation and reasoning, computer vision, neural computation, and natural language processing. The seminar consisted of contributed and invited talks, breakout and joint group discussion sessions, and a hackathon. It was built upon previous seminars and workshops on the integration of computational learning and symbolic reasoning, such as the Neural-Symbolic Learning and Reasoning (NeSy) workshop series, and the previous Dagstuhl Seminar 14381: Neural-Symbolic Learning and Reasoning.

This report documents the program and the outcomes of Dagstuhl Seminar 17192 "Human-Like Neural-Symbolic Computing", held from May 7th to 12th, 2017. The underlying idea of Human-Like Computing is to incorporate into Computer Science aspects of how humans learn, reason and compute. Whilst recognising the relevant scientific trends in big data and deep learning, capable of achieving state-of-the-art performance in speech recognition and computer vision tasks, limited progress has been made towards understanding the principles underlying language and vision understanding. Under the assumption that neural-symbolic computing - the study of logic and connectionism as well statistical approaches - can offer new insight into this problem, the seminar brought together computer scientists, but also specialists on artificial intelligence, cognitive science, machine learning, knowledge representation and reasoning, computer vision, neural computation, and natural language processing. The seminar consisted of contributed and invited talks, breakout and joint group discussion sessions, and a hackathon. It was built upon previous seminars and workshops on the integration of computational learning and symbolic reasoning, such as the Neural-Symbolic Learning and Reasoning (NeSy) workshop series, and the previous Dagstuhl Seminar 14381: Neural-Symbolic Learning and Reasoning.

This report documents the program and the outcomes of Dagstuhl Seminar 14381 "Neural-Symbolic Learning and Reasoning", which was held from September 14th to 19th, 2014. This seminar brought together specialist in machine learning, knowledge representation and reasoning, computer vision and image understanding, natural language processing, and cognitive science. The aim of the seminar was to explore the interface among several fields that contribute to the effective integration of cognitive abilities such as learning, reasoning, vision and language understanding in intelligent and cognitive computational systems. The seminar consisted of contributed and invited talks, breakout and joint group discussion sessions.

This report documents the program and the outcomes of Dagstuhl Seminar 14381 "Neural-Symbolic Learning and Reasoning", which was held from September 14th to 19th, 2014. This seminar brought together specialist in machine learning, knowledge representation and reasoning, computer vision and image understanding, natural language processing, and cognitive science. The aim of the seminar was to explore the interface among several fields that contribute to the effective integration of cognitive abilities such as learning, reasoning, vision and language understanding in intelligent and cognitive computational systems. The seminar consisted of contributed and invited talks, breakout and joint group discussion sessions.

Neural-symbolic computation aims at integrating robust connectionist learning algorithms with sound symbolic rea-soning. The recent impact of neural learning, in particular of deep networks, has led to the creation of new representa-tions that have, so far, not really been used for reasoning. Results on neural-symbolic computation have shown to of-fer powerful alternatives for knowledge representation, learning and inference in neural computation. This paper presents key challenges and contributions of neural-symbolic computation to this area.

Deep Boltzmann Machines (DBM) have been used as a computational cognitive model in various AI-related research and applications, notably in computational vision and multimodal fusion. Being regarded as a biological plausible model of the human brain, the DBM is also becoming a popular instrument to investigate various cortical processes in neuroscience. In this paper, we describe how a multimodal DBM is implemented as part of a Neural-Symbolic Cognitive Agent (NSCA) for real-time multimodal fusion and inference of streaming audio and video data. We describe how this agent can be used to simulate certain neurological mechanisms related to hallucinations and dreaming and how these mechanisms are beneficial to the integrity of the DBM. Finally, we will explain how the NSCA is used to extract multimodal information from the DBM and provide a compact and practical iconographic temporal logic formula for complex relations between visual and auditory patterns.

Deep Boltzmann Machines (DBM) have been used as a computational cognitive model in various AI-related research and applications, notably in computational vision and multimodal fusion. Being regarded as a biological plausible model of the human brain, the DBM is also becoming a popular instrument to investigate various cortical processes in neuroscience. In this paper, we describe how a multimodal DBM is implemented as part of a Neural-Symbolic Cognitive Agent (NSCA) for real-time multimodal fusion and inference of streaming audio and video data. We describe how this agent can be used to simulate certain neurological mechanisms related to hallucinations and dreaming and how these mechanisms are beneficial to the integrity of the DBM. Finally, we will explain how the NSCA is used to extract multimodal information from the DBM and provide a compact and practical iconographic temporal logic formula for complex relations between visual and auditory patterns.

The AAAI-12 Workshop program was held Sunday and Monday, July 22-23, 2012, at the Sheraton Centre Toronto Hotel in Toronto, Ontario, Canada. The AAAI-12 workshop program included nine workshops covering a wide range of topics in artificial intelligence. T

In this paper we provide a neural-symbolic framework to model, reason about and learn norms in multi-agent systems. To this purpose, we define a fragment of Input/Output (I/O) logic that can be embedded into a neural network. We extend d’Avila Garcez et al. Connectionist Inductive Learning and Logic Programming System (CILP) to translate an I/O logic theory into a Neural Network (NN) that can be trained further with examples: we call this new system Normative- CILP (N-CILP). We then present a new algorithm to handle priorities between rules in order to cope with normative issues like Contrary to Duty (CTD), Priorities, Exceptions and Permissions. We illustrate the applicability of the framework on a case study based on RoboCup rules: within this working example, we compare the learning capacity of a network built with N-CILP with a non symbolic neural net- work, we explore how the initial knowledge impacts on the overall performance, and we test the NN capacity of learn- ing norms, generalizing new Contrary to Duty rules from examples.

In this paper we provide a neural-symbolic framework to model, reason about and learn norms in multi-agent systems. To this purpose, we define a fragment of Input/Output (I/O) logic that can be embedded into a neural network. We extend d’Avila Garcez et al. Connectionist Inductive Learning and Logic Programming System (CILP) to translate an I/O logic theory into a Neural Network (NN) that can be trained further with examples: we call this new system Normative- CILP (N-CILP). We then present a new algorithm to handle priorities between rules in order to cope with normative issues like Contrary to Duty (CTD), Priorities, Exceptions and Permissions. We illustrate the applicability of the framework on a case study based on RoboCup rules: within this working example, we compare the learning capacity of a network built with N-CILP with a non symbolic neural net- work, we explore how the initial knowledge impacts on the overall performance, and we test the NN capacity of learn- ing norms, generalizing new Contrary to Duty rules from examples.

Normative systems are dynamic systems because their rules can change over time. Considering this problem, we propose a neural- symbolic approach to provide agents the instru- ments to reason about and learn norms in a dynamic environment. We propose a variant of d’Avila Garcez et al. Con- nectionist Inductive Learning and Logic Program- ming(CILP) System to embed Input/Output logic normative rules into a feed-forward neural network. The resulting system called Normative-CILP(N- CILP) shows how neural networks can cope with some of the underpinnings of normative reasoning: permissions , dilemmas , exceptions and contrary to duty problems. We have applied our approach in a simplified RoboCup environment, using the N-CILP simula- tor that we have developed. In the concluding part of the paper, we provide some of the results ob- tained in the experiments

In this paper we propose a neural-symbolic architecture to represent and reason with norms in multi-agent systems. On the one hand, the architecture contains a symbolic knowledge base to represent norms and on the other hand it contains a neural network to reason with norms. The interaction between the symbolic knowledge and the neural network is used to learn norms. We describe how to handle normative reasoning issues like contrary to duties, dilemmas and exceptions by using a priority-based ordering between the norms in a neural-symbolic architecture.

Normative systems are dynamic systems because their rules can change over time. Considering this problem, we propose a neural- symbolic approach to provide agents the instru- ments to reason about and learn norms in a dynamic environment. We propose a variant of d’Avila Garcez et al. Con- nectionist Inductive Learning and Logic Program- ming(CILP) System to embed Input/Output logic normative rules into a feed-forward neural network. The resulting system called Normative-CILP(N- CILP) shows how neural networks can cope with some of the underpinnings of normative reasoning: permissions , dilemmas , exceptions and contrary to duty problems. We have applied our approach in a simplified RoboCup environment, using the N-CILP simula- tor that we have developed. In the concluding part of the paper, we provide some of the results ob- tained in the experiments

In this paper we propose a neural-symbolic architecture to represent and reason with norms in multi-agent systems. On the one hand, the architecture contains a symbolic knowledge base to represent norms and on the other hand it contains a neural network to reason with norms. The interaction between the symbolic knowledge and the neural network is used to learn norms. We describe how to handle normative reasoning issues like contrary to duties, dilemmas and exceptions by using a priority-based ordering between the norms in a neural-symbolic architecture.

We discuss the purpose of neural-symbolic integration including its principles, mechanisms and applications. We outline a cognitive computational model for neural-symbolic integration, position the model in the broader context of multi-agent systems, machine learning and automated reasoning, and list some of the challenges for the area of neural-symbolic computation to achieve the promise of effective integration of robust learning and expressive reasoning under uncertainty.

We discuss the purpose of neural-symbolic integration including its principles, mechanisms and applications. We outline a cognitive computational model for neural-symbolic integration, position the model in the broader context of multi-agent systems, machine learning and automated reasoning, and list some of the challenges for the area of neural-symbolic computation to achieve the promise of effective integration of robust learning and expressive reasoning under uncertainty.