Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge...
详细信息
ISBN:
(纸本)9781713845393
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. The first key idea in Edge Transformers is to associate vector states with every edge, that is, with every pair of input nodes-as opposed to just every node, as it is done in the Transformer model. The second major innovation is a triangular attention mechanism that updates edge representations in a way that is inspired by unification from logic programming. We evaluate Edge Transformer on compositional generalization benchmarks in relational reasoning, semantic parsing, and dependency parsing(1). In all three settings, the Edge Transformer outperforms Relation-aware, Universal and classical Transformer baselines.
Reaction Systems (RSs) are a successful natural computing framework inspired by chemical reaction networks. A RS consists of a set of entities and a set of reactions. Entities can enable or inhibit each reaction, and ...
详细信息
ISBN:
(纸本)9783030904258;9783030904241
Reaction Systems (RSs) are a successful natural computing framework inspired by chemical reaction networks. A RS consists of a set of entities and a set of reactions. Entities can enable or inhibit each reaction, and are produced by reactions or provided by the environment. In a previous paper, we defined an original labelled transition system (LTS) semantics for RSs in the structural operational semantics (SOS) style. This approach has several advantages: (i) it provides a formal specification of the RS dynamics that enables the reuse of many formal analysis techniques and favors the implementation of tools, and (ii) it facilitates the definition of extensions of the RS framework by simply modifying some of the SOS rules in a modular way. In this paper, we demonstrate the extensibility of the framework by defining two quantitative variants of RSs: with reaction delays/durations, and with concentration levels. We provide a prototype logic programming implementation and apply our tool to a RS model of Th cells differentiation in the immune system.
Autonomy in robot-assisted surgery is essential to reduce surgeons' cognitive load and eventually improve the overall surgical outcome. A key requirement for autonomy in a safety-critical scenario as surgery lies ...
详细信息
ISBN:
(纸本)9781665406222
Autonomy in robot-assisted surgery is essential to reduce surgeons' cognitive load and eventually improve the overall surgical outcome. A key requirement for autonomy in a safety-critical scenario as surgery lies in the generation of interpretable plans that rely on expert knowledge. Moreover, the Autonomous Robotic Surgical System (ARSS) must be able to reason on the dynamic and unpredictable anatomical environment, and quickly adapt the surgical plan in case of unexpected situations. In this paper, we present a modular Framework for Robot-Assisted Surgery (FRAS) in deformable anatomical environments. Our framework integrates a logic module for task-level interpretable reasoning, a biomechanical simulation that complements data from real sensors, and a situation awareness module for context interpretation. The framework performance is evaluated on simulated soft tissue retraction, a common surgical task to remove the tissue hiding a region of interest. Results show that the framework has the adaptability required to successfully accomplish the task, handling dynamic environmental conditions and possible failures, while guaranteeing the computational efficiency required in a real surgical scenario. The framework is made publicly available.
Multi-agent systems research community has developed solutions to model dynamic and complex systems. Those solutions have generated a growing interest in a variety of domains such as robotics or distributed controls. ...
详细信息
ISBN:
(纸本)9781665409698
Multi-agent systems research community has developed solutions to model dynamic and complex systems. Those solutions have generated a growing interest in a variety of domains such as robotics or distributed controls. It is therefore important to build solutions to analyze the basic mechanisms of multi-agent systems such as interaction. In this paper, we formalize the epistemic interaction, we propose to use default theory to describe state transitions. The introduction of such semantics allows characterizing the verification of agent behavior when dealing with new information. Therefore, we introduce semantics to establish a basis for exploiting the properties of the agent behavior and its messages. We propose to formalize and verify the response of an agent when it receives a new information from another agent of its environment. Our approach extends the actions initiated in the mA* [5] language by applying the Reiter's default rules [32]. A simple example is used to illustrate our approach.
Wine production and vineyard work are seasonal activities as there is a period when no intervention is required and oenotourism may fill that void. On the other hand, given that grapevines are tied to this area of act...
详细信息
ISBN:
(纸本)9783030726508;9783030726515
Wine production and vineyard work are seasonal activities as there is a period when no intervention is required and oenotourism may fill that void. On the other hand, given that grapevines are tied to this area of activity, it is of paramount importance to assess customer and staff awareness of the health risks of pesticide use, that emerge from people's responses to specific questionnaires. Therefore, a workable problem-solving method is proposed which enables one to assess the level of awareness of people who are taking on the risks, evaluated in terms of an estimation of the individuals entropic state with respect to this particular issue. The analysis and development of such a model is based on a number of logic programming formalisms for Knowledge Representation and Reasoning, tha are consistent with an Artificial Neural Network approach to computing. The data collection process involved 173 participants. The proposed system presents an accuracy of about 90% and enables the diagnosis of risk awareness and the correspondent fragilities among customers and staff for a particular pesticide.
JDart performs dynamic symbolic execution of Java programs: it executes programs with concrete inputs while recording symbolic constraints on executed program paths. A portfolio of constraint solvers is then used for ...
详细信息
ISBN:
(纸本)9783030720124;9783030720131
JDart performs dynamic symbolic execution of Java programs: it executes programs with concrete inputs while recording symbolic constraints on executed program paths. A portfolio of constraint solvers is then used for generating new concrete values from recorded constraints that drive execution along previously unexplored paths. For SV-COMP 2021, we improved JDart by implementing exploration strategies, bounded analysis, and path-specific constraint solving strategies, as well as by enabling the use of SMT-Lib string theory for encoding of string operations.
Answer Set programming (ASP) is a successful method for solving a range of real-world applica-tions. Despite the availability of fast ASP solvers, computing answer sets demands a very large computational power, since ...
详细信息
Answer Set programming (ASP) is a successful method for solving a range of real-world applica-tions. Despite the availability of fast ASP solvers, computing answer sets demands a very large computational power, since the problem tackled is in the second level of the polynomial hierarchy. A speed-up in answer set computation may be attained, if the program can be split into two disjoint parts, bottom and top. Thus, the bottom part is evaluated independently of the top part, and the results of the bottom part evaluation are used to simplify the top part. Lifschitz and Turner have introduced the concept of a splitting set, i.e., a set of atoms that defines the *** this paper, We show that the problem of computing a splitting set with some desirable prop-erties can be reduced to a classic Search Problem and solved in polynomial time. This allows us to conduct experiments on the size of the splitting set in various programs and lead to an interesting discoery of a source of complication in stable model computation. We also show that for Head -Cycle-Free programs, the definition of splitting sets can be adjusted to allow splitting of a broader class of programs.
This paper presents a framework for enforcing penalties on intelligent agents that do not comply with authorization or obligation policies in a changing environment. A framework is proposed to represent and reason abo...
详细信息
Both Prolog and Oz are multiparadigm languages with a logic programming core. There is a significant subset of Oz that is a syntactic variant of Prolog: pure Prolog programs with green or blue cuts and bagof/3 or seto...
详细信息
While deep neural networks have led to major advances in image recognition, language translation, data mining, and game playing, there are well-known limits to the paradigm such as lack of explainability, difficulty o...
详细信息
暂无评论