scholarly journals Synbit: synthesizing bidirectional programs using unidirectional sketches

2021 ◽  
Vol 5 (OOPSLA) ◽  
pp. 1-31
Author(s):  
Masaomi Yamaguchi ◽  
Kazutaka Matsuda ◽  
Cristina David ◽  
Meng Wang
Keyword(s):  
Programming Language ◽  
State Of The Art ◽  
Input Output ◽  
Program Structure ◽  
The Core ◽  
Synthesis Tool ◽  
The Given

We propose a technique for synthesizing bidirectional programs from the corresponding unidirectional code plus a few input/output examples. The core ideas are: (1) constructing a sketch using the given unidirectional program as a specification, and (2) filling the sketch in a modular fashion by exploiting the properties of bidirectional programs. These ideas are enabled by our choice of programming language, HOBiT, which is specifically designed to maintain the unidirectional program structure in bidirectional programming, and keep the parts that control bidirectional behavior modular. To evaluate our approach, we implemented it in a tool called Synbit and used it to generate bidirectional programs for intricate microbenchmarks, as well as for a few larger, more realistic problems. We also compared Synbit to a state-of-the-art unidirectional synthesis tool on the task of synthesizing backward computations.

scholarly journals A novel optimal multi-pattern matching method with wildcards for DNA sequence

2021 ◽  
Vol 29 ◽  
pp. 115-124
Author(s):  
Xinlu Wang ◽  
Ahmed A.F. Saif ◽  
Dayou Liu ◽  
Yungang Zhu ◽  
Jon Atli Benediktsson
Keyword(s):  
Dna Sequence ◽  
Pattern Matching ◽  
Health Informatics ◽  
State Of The Art ◽  
Machine Language ◽  
Data Sets ◽  
Fundamental Issue ◽  
Matching Method ◽  
Dna Sequence Alignment ◽  
The Given

BACKGROUND: DNA sequence alignment is one of the most fundamental and important operation to identify which gene family may contain this sequence, pattern matching for DNA sequence has been a fundamental issue in biomedical engineering, biotechnology and health informatics. OBJECTIVE: To solve this problem, this study proposes an optimal multi pattern matching with wildcards for DNA sequence. METHODS: This proposed method packs the patterns and a sliding window of texts, and the window slides along the given packed text, matching against stored packed patterns. RESULTS: Three data sets are used to test the performance of the proposed algorithm, and the algorithm was seen to be more efficient than the competitors because its operation is close to machine language. CONCLUSIONS: Theoretical analysis and experimental results both demonstrate that the proposed method outperforms the state-of-the-art methods and is especially effective for the DNA sequence.

scholarly journals Question-aware memory network for multi-hop question answering in human–robot interaction

2021 ◽  
Author(s):  
Xinmeng Li ◽  
Mamoun Alazab ◽  
Qian Li ◽  
Keping Yu ◽  
Quanjun Yin
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Human Robot Interaction ◽  
Knowledge Graph ◽  
Robot Interaction ◽  
Natural Language Question ◽  
Memory Network ◽  
The Given ◽  
Fine Tune ◽  
Language Question

AbstractKnowledge graph question answering is an important technology in intelligent human–robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge graph. For the multi-relation question with higher variety and complexity, the tokens of the question have different priority for the triples selection in the reasoning steps. Most existing models take the question as a whole and ignore the priority information in it. To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process. In addition, we incorporate graph context information into knowledge graph embedding model to increase the ability to represent entities and relations. We use it to initialize the QA2MN model and fine-tune it in the training process. We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering. The result demonstrates that QA2MN achieves state-of-the-art Hits@1 accuracy on the two datasets, which validates the effectiveness of our model.

scholarly journals On the formation and stability of fermionic dark matter halos in a cosmological framework

2020 ◽  
Author(s):  
Carlos R Argüelles ◽  
Manuel I Díaz ◽  
Andreas Krut ◽  
Rafael Yunis
Keyword(s):  
Black Hole ◽  
Dark Matter ◽  
Space Distribution ◽  
Coarse Grained ◽  
Dark Matter Halos ◽  
The Core ◽  
The Galaxy ◽  
Gravitating Systems ◽  
The Given ◽  
First Time

Abstract The formation and stability of collisionless self-gravitating systems is a long standing problem, which dates back to the work of D. Lynden-Bell on violent relaxation, and extends to the issue of virialization of dark matter (DM) halos. An important prediction of such a relaxation process is that spherical equilibrium states can be described by a Fermi-Dirac phase-space distribution, when the extremization of a coarse-grained entropy is reached. In the case of DM fermions, the most general solution develops a degenerate compact core surrounded by a diluted halo. As shown recently, the latter is able to explain the galaxy rotation curves while the DM core can mimic the central black hole. A yet open problem is whether this kind of astrophysical core-halo configurations can form at all, and if they remain stable within cosmological timescales. We assess these issues by performing a thermodynamic stability analysis in the microcanonical ensemble for solutions with given particle number at halo virialization in a cosmological framework. For the first time we demonstrate that the above core-halo DM profiles are stable (i.e. maxima of entropy) and extremely long lived. We find the existence of a critical point at the onset of instability of the core-halo solutions, where the fermion-core collapses towards a supermassive black hole. For particle masses in the keV range, the core-collapse can only occur for Mvir ≳ E9M⊙ starting at zvir ≈ 10 in the given cosmological framework. Our results prove that DM halos with a core-halo morphology are a very plausible outcome within nonlinear stages of structure formation.

scholarly journals A modular framework to generate robust biped locomotion: from planning to control

2021 ◽  
Vol 3 (9) ◽  
Author(s):  
Mohammadreza Kasaei ◽  
Ali Ahmadi ◽  
Nuno Lau ◽  
Artur Pereira
Keyword(s):  
Numerical Simulations ◽  
Predictive Control ◽  
Biped Locomotion ◽  
Input Output ◽  
Dynamics Model ◽  
Biped Robots ◽  
The Core ◽  
Simulation Results ◽  
Reference Trajectories ◽  
Modular Framework

AbstractBiped robots are inherently unstable because of their complex kinematics as well as dynamics. Despite many research efforts in developing biped locomotion, the performance of biped locomotion is still far from the expectations. This paper proposes a model-based framework to generate stable biped locomotion. The core of this framework is an abstract dynamics model which is composed of three masses to consider the dynamics of stance leg, torso, and swing leg for minimizing the tracking problems. According to this dynamics model, we propose a modular walking reference trajectories planner which takes into account obstacles to plan all the references. Moreover, this dynamics model is used to formulate the controller as a Model Predictive Control (MPC) scheme which can consider some constraints in the states of the system, inputs, outputs, and also mixed input-output. The performance and the robustness of the proposed framework are validated by performing several numerical simulations using MATLAB. Moreover, the framework is deployed on a simulated torque-controlled humanoid to verify its performance and robustness. The simulation results show that the proposed framework is capable of generating biped locomotion robustly.

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals Mind mapping as a tool of teaching English vocabulary at transport university

2021 ◽  
Vol 295 ◽  
pp. 05021
Author(s):  
Oksana Marunevich ◽  
Elmira Shefieva ◽  
Olga Bessarabova
Keyword(s):  
Educational Process ◽  
Control Group ◽  
Teaching English ◽  
Mind Mapping ◽  
New Words ◽  
The Core ◽  
Mind Maps ◽  
The Given ◽  
Core Problem ◽  
Experimental Group

The core problem of teaching English as a second language at transport university is students’ poor knowledge of vocabulary. Current solutions to the given problem such as providing word explanations and repetitive practices are ineffective. We strongly believe that the mindmapping technique proposed by Tony Buzan as a note-taking method is a novel, yet an extremely potent tool that aids students in enlarging their professional word stock by associating new vocabulary to their existing knowledge using colors, images, symbols, etc. As might have been expected, the findings of our study point towards the idea that the strong visual appeal of mind maps created by easy-to-use software boosted the educational process and helped students of the experimental group memorize more new words in contrast to students of the control group.

scholarly journals A Runtime System for XML Transformations in Java

2004 ◽  
Vol 11 (33) ◽  
Author(s):  
Aske Simon Christensen ◽  
Christian Kirkegaard ◽  
Anders Møller
Keyword(s):  
Static Analysis ◽  
Programming Language ◽  
Program Analysis ◽  
Companion Paper ◽  
General Purpose ◽  
Runtime System ◽  
Xml Documents ◽  
Level Data ◽  
High Level ◽  
The Given

We show that it is possible to extend a general-purpose programming language with a convenient high-level data-type for manipulating XML documents while permitting (1) precise static analysis for guaranteeing validity of the constructed XML documents relative to the given DTD schemas, and (2) a runtime system where the operations can be performed efficiently. The system, named Xact, is based on a notion of immutable XML templates and uses XPath for deconstructing documents. A companion paper presents the program analysis; this paper focuses on the efficient runtime representation.

scholarly journals Exemplar Guided Neural Dialogue Generation

2020 ◽  
Author(s):  
Hengyi Cai ◽  
Hongshen Chen ◽  
Yonghao Song ◽  
Xiaofang Zhao ◽  
Dawei Yin
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Small Subset ◽  
Generation Model ◽  
Retrieval Model ◽  
Training Set ◽  
Dialogue Model ◽  
Quantitative Metrics ◽  
The Given

Humans benefit from previous experiences when taking actions. Similarly, related examples from the training data also provide exemplary information for neural dialogue models when responding to a given input message. However, effectively fusing such exemplary information into dialogue generation is non-trivial: useful exemplars are required to be not only literally-similar, but also topic-related with the given context. Noisy exemplars impair the neural dialogue models understanding the conversation topics and even corrupt the response generation. To address the issues, we propose an exemplar guided neural dialogue generation model where exemplar responses are retrieved in terms of both the text similarity and the topic proximity through a two-stage exemplar retrieval model. In the first stage, a small subset of conversations is retrieved from a training set given a dialogue context. These candidate exemplars are then finely ranked regarding the topical proximity to choose the best-matched exemplar response. To further induce the neural dialogue generation model consulting the exemplar response and the conversation topics more faithfully, we introduce a multi-source sampling mechanism to provide the dialogue model with both local exemplary semantics and global topical guidance during decoding. Empirical evaluations on a large-scale conversation dataset show that the proposed approach significantly outperforms the state-of-the-art in terms of both the quantitative metrics and human evaluations.

scholarly journals Optimization Learning: Perspective, Method, and Applications

2020 ◽  
Author(s):  
Risheng Liu
Keyword(s):  
Inverse Problems ◽  
Theoretical Analysis ◽  
Iterative Methods ◽  
State Of The Art ◽  
Learning Paradigm ◽  
Rigorous Analysis ◽  
The Core ◽  
Globally Convergent ◽  
Ill Posed ◽  
Art Performance

Numerous tasks at the core of statistics, learning, and vision areas are specific cases of ill-posed inverse problems. Recently, learning-based (e.g., deep) iterative methods have been empirically shown to be useful for these problems. Nevertheless, integrating learnable structures into iterations is still a laborious process, which can only be guided by intuitions or empirical insights. Moreover, there is a lack of rigorous analysis of the convergence behaviors of these reimplemented iterations, and thus the significance of such methods is a little bit vague. We move beyond these limits and propose a theoretically guaranteed optimization learning paradigm, a generic and provable paradigm for nonconvex inverse problems, and develop a series of convergent deep models. Our theoretical analysis reveals that the proposed optimization learning paradigm allows us to generate globally convergent trajectories for learning-based iterative methods. Thanks to the superiority of our framework, we achieve state-of-the-art performance on different real applications.

scholarly journals Asymmetric Distribution Measure for Few-shot Learning

2020 ◽  
Author(s):  
Wenbin Li ◽  
Lei Wang ◽  
Jing Huo ◽  
Yinghuan Shi ◽  
Yang Gao ◽  
...  
Keyword(s):  
State Of The Art ◽  
Asymmetric Distribution ◽  
Query Image ◽  
Local Descriptor ◽  
Innovative Design ◽  
Feature Representations ◽  
The Core ◽  
Measure Function ◽  
Asymmetric Relation ◽  
Core Idea

The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relation between a query image and a support class. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of a query and a class. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, ADM can achieve the state-of-the-art results, validating our innovative design of asymmetric distribution measures for few-shot learning. The source code can be downloaded from https://github.com/WenbinLee/ADM.git.

Sign in / Sign up

Export Citation Format

Share Document