the proceedings contain 21 papers. the topics discussed include: planning safe collaborative behaviors through risk-aware heuristic search;tabular model learning in Monte Carlo tree search;goal recognition with deep l...
the proceedings contain 21 papers. the topics discussed include: planning safe collaborative behaviors through risk-aware heuristic search;tabular model learning in Monte Carlo tree search;goal recognition with deep learning and embedded representation of state traces;investigating domain-oriented approaches to optimization in timeline-based planning;heuristic planning for hybrid dynamical systems with constraint logicprogramming;characterizing nexus of similarity between entities;a simple proof-theoretic characterization of stable models;experimenting an approach to neuro-symbolic RL;planning as theorem proving with heuristics;learning augmented online learning algorithms - the adversarial bandit with knapsacks framework;and optimal rates for online Bayesian persuasion.
Task constraint feedback is the collective name for any kind of feedback system that checks whether problem-defined constraints were fulfilled by students upon submission of work. this can be as simple as checking if ...
详细信息
ISBN:
(纸本)9789869721493
Task constraint feedback is the collective name for any kind of feedback system that checks whether problem-defined constraints were fulfilled by students upon submission of work. this can be as simple as checking if certain programming constructs exist, or if a specific algorithm or data structure required by the problem is fulfilled. Most of these systems use static analysis (Fischer, 2006;Gotel, 2008) or natural language processing techniques (Lane, 2005) to generate feedback. A transformer is a neural network for sequence processing, such as natural languages. Previous work has shown that transformers can be generalized for programming language tasks such as code summarization. In this study, we used the CodeBERT transformer to classify or tag algorithms implemented in some code snippets to check constraint satisfaction. Using a custom dataset containing source code aiming to implement algorithms, we show that CodeBERT is capable of learning structures of how code is implemented regardless of how a programmer names the code. Averaging each label's f1-score, the model was able to obtain an average of 0.85, which showed promising results in the dataset.
this work revisits the topic of jointly parsing constituency and dependency trees, i.e., to produce compatible constituency and dependency trees simultaneously for input sentences, which is attractive considering that...
详细信息
Code search is an important and well-studied task, but it usually means searching for code by a text query. We argue that using a code snippet (and possibly an error traceback) as a query while looking for bugfixing i...
详细信息
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). the core challenge of this task lies in understanding the complex semantic infor...
详细信息
Integer Linear programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI). However, traditional ILP frameworks are non-differentiab...
详细信息
the use of computational memories based on ReRAM technology is currently being explored for the next-generation energy-efficient computing-in-memory (CIM) systems. Such approach presents major challenges at device, ci...
详细信息
ISBN:
(数字)9781665490054
ISBN:
(纸本)9781665490054
the use of computational memories based on ReRAM technology is currently being explored for the next-generation energy-efficient computing-in-memory (CIM) systems. Such approach presents major challenges at device, circuit, and application level. thus, this MSc thesis work aims to establish a roadmap towards technologically-viable solutions for the design and development of industrially appealing ReRAM-based CIM systems. To this end, we comment on the major steps in the SW-HW co-design to develop the memory array driving circuitry that will support memory and logic operations based on non-stateful logic primitives. the latter are expected to be variability-agnostic and not to rely computations on probabilistic switching of memristors. Furthermore, we highlight the requirement for synthesis algorithms designed adhoc for CIM systems, compatible withthe peripheral circuitry of the ReRAM and the underlying logic primitives, which will produce delay/area-efficient execution of an arbitrary logic function in memory. the complete toolkit resulting from the proposed roadmap is expected to accelerate the industrial establishment of resistive CIM systems through the development of functional prototypes, fully compatible with imperfections of ReRAM devices, thus useful for immediate practical exploitation by the relevant industry.
Due to the incorporation of heterogeneous cores in modern multi-core systems, the exploitation of their full potential strongly depends on the proper mapping of an application to the platform. this work presents an ap...
详细信息
ISBN:
(数字)9781665490054
ISBN:
(纸本)9781665490054
Due to the incorporation of heterogeneous cores in modern multi-core systems, the exploitation of their full potential strongly depends on the proper mapping of an application to the platform. this work presents an approach to map static applications on heterogeneous platforms minimizing their makespan based on the Benders decomposition principle combined with an Integer Linear programming (ILP) model. the proposed approach adopts a three-stage decomposition scheme, finding permutations of infeasible solutions to generate multiple cuts in every iteration. the first stage deals withthe assignment of the tasks to the cores and the last one withtheir scheduling, whereas the second stage propagates new bounds based on the current assignment and provides an explanation of the infeasibility in the form of subsets of assignment variables. Based on that, other infeasible combinations are computed by checking their permutations and more Benders cuts are produced. the proposed method is compared with a two-stage decomposition approach and an ILP model and exhibits better performance in terms of solution time and number solved instances to optimality.
While several learning support systems that visualize program behaviors for various object-oriented languages have been developed to date, many of them are not sufficient for learners to understand the concepts specif...
详细信息
ISBN:
(纸本)9789869721493
While several learning support systems that visualize program behaviors for various object-oriented languages have been developed to date, many of them are not sufficient for learners to understand the concepts specific to object-oriented languages. We have developed a program visualization system that supports learners' understanding by visualizing relationships among objects and classes. We evaluated the effectiveness of our system by introducing it into an actual class and measuring the degree of improvement in learners' understanding based on tests. the evaluation results suggest that our system would have a certain degree of effectiveness for learning programming using object-oriented languages.
We extend the Soft Linear logic of Lafont with a new kind of modality, called parallel. Contractions on parallel modalities are only allowed in the cut and the left ⊸ rules, in a controlled, uniformly distributive way...
详细信息
暂无评论