scholarly journals Predicting Propositional Satisfiability via End-to-End Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 3324-3331
Author(s):  
Chris Cameron ◽  
Rex Chen ◽  
Jason Hartford ◽  
Kevin Leyton-Brown
Keyword(s):  
Linear Time ◽  
Network Models ◽  
Problem Size ◽  
Linear Programming Relaxations ◽  
Deep Networks ◽  
Solution Methods ◽  
End To End ◽  
Complex Features ◽  
First Time ◽  
Random Guessing

Strangely enough, it is possible to use machine learning models to predict the satisfiability status of hard SAT problems with accuracy considerably higher than random guessing. Existing methods have relied on extensive, manual feature engineering and computationally complex features (e.g., based on linear programming relaxations). We show for the first time that even better performance can be achieved by end-to-end learning methods — i.e., models that map directly from raw problem inputs to predictions and take only linear time to evaluate. Our work leverages deep network models which capture a key invariance exhibited by SAT problems: satisfiability status is unaffected by reordering variables and clauses. We showed that end-to-end learning with deep networks can outperform previous work on random 3-SAT problems at the solubility phase transition, where: (1) exactly 50% of problems are satisfiable; and (2) empirical runtimes of known solution methods scale exponentially with problem size (e.g., we achieved 84% prediction accuracy on 600-variable problems, which take hours to solve with state-of-the-art methods). We also showed that deep networks can generalize across problem sizes (e.g., a network trained only on 100-variable problems, which typically take about 10 ms to solve, achieved 81% accuracy on 600-variable problems).

scholarly journals A unique mating pattern of Panorpodes kuandianensis (Mecoptera: Panorpodidae)

2017 ◽  
Vol 86 (3) ◽  
pp. 229-237 ◽  
Author(s):  
Xin Tong ◽  
Lu Jiang ◽  
Bao-Zhen Hua
Keyword(s):  
Mating Behavior ◽  
Sexual Conflict ◽  
Sperm Transfer ◽  
Nuptial Gift ◽  
Mating Pattern ◽  
End To End ◽  
Mating Behaviors ◽  
First Time

Sexually reproductive insects exhibit diverse mating behaviors. However, the mating pattern remains unknown for Panorpodes of Panorpodidae to date. In this study, we investigated the mating behavior and copulatory mechanism of the short-faced scorpionfly Panorpodes kuandianensis Zhong, Zhang and Hua, 2011 for the first time. The results show that the male provides a salivary mass as a nuptial gift to the female and starts to copulate with the female in a V-shaped position, then changes to an end-to-end position by temporarily twisting the female abdominal segments VII−IX by 180°. During mating the basal processes and the basal teeth of the gonostyli and the hypandrium are used to obtain copulation and sustain the coupling of genitalia to secure successful sperm transfer. This unique mating pattern is greatly different from that of other Mecoptera reported and is likely evolved as an adaptation in the context of sexual conflict.

scholarly journals GRANITOIDS, RARE-METAL PEGMATITES AND Ta-Nb MINERALIZATION OF SHPOLIANO-TASHLYK ORE AREA (INGUL MEGABLOCK, UKRAINIAN SHIELD)

2018 ◽  
pp. 24-29
Author(s):  
O. Hrinchenko ◽  
S. Bondarenko ◽  
T. Mironchuk
Keyword(s):  
Rare Metal ◽  
Ukrainian Shield ◽  
Wide Range ◽  
Ore Minerals ◽  
Ore Mineralization ◽  
Isomorphic Series ◽  
Single Complex ◽  
Complex Features ◽  
First Time ◽  
Range Of Values

Composition of granites, genetically associated pegmatites and superimposed metasomatites distributed within Shpoliano-Tashlyk ore area (Ingul megablock) is considered. It is established, that on the basis of similarity in their petrographic and petrochemical features granitoids of the area can be related to single complex. Features of ore mineralization are defined by both composition of granitoids (Sgranites) after which rare-metal pegmatites are formed and intensity of superimposed metasomatic alterations. Main minerals-concentrators of Ta and Nb mineralization in granitic pegmatites and metasomatites are represented by minerals of three isomorphic series – columbite-tantalite (Fe,Mn)(Nb,Ta,Ti)2O6, ilmenorutile-struverite (Ti,Nb,Ta)O2 and pyrochlore-microlite (Ca,Na)2Ta2O6(O,B,OH,F). Depending on geological setting such ore minerals as tapiolite, ixiolite, cassiterite, uraninite, nigerite, gahnite are commonly found in association with these minerals. Chemical composion of tantalo-niobates sampled from ore-bearing pegmatites and metasomatites is investigated by microprobe analysis. Most minerals of columbite-tantalite series are characterized by distinct and rhythmic internal zonality and contrasting mosaic structure which are related to considerable heterogeneities of their chemical composition. Within one aggregate mineral phases with wide range of values – from 9,80 to 71,0 % for Ta2O5 and from 10,6 to 70,1 % for Nb2O5 – are established. Among minerals ferruginous varieties which composition relates to Fe-columbite-tantalites (Nb2O5/Ta2O5 = 1–1,2; FeO/MnO = 2,5–6) prevail. Columbite-tantalites are characterised by high contents of admixture elements present (%): TiO2 – to 5,88; WO3 – to 3,70; SnO2 – to 9,20; Sc2O3 – to 5,40. Scandium ores occur as scandium-rich minerals that are mostly confined to the minerals of columbite-tantalite series found in Polohivka ore field. On the Ukrainian Shield high contents of Sc2O3 in tantalo-niobates are established for the first time. Minerals of ilmenorutile-struverite series do not quantitatively yield to minerals of columbite-tantalite series. For minerals of this series Nb2O5/Ta2O5 ratio varies in the range of 0,6-1,4. Among characteristic admixture-elements are prevailed (%): SnO2 – to 3,1, V2O5 – to 5,05; FeO – to 11,51, Cr2O3 – to 1,20. Minerals of pyrochlore-microlite series are of subordinate importance. For the first time by results of U-Pb dating of columbite-tantalites from Mostove ore manifestation (Shpoliano-Tashlyk area) the age of Ta-Nb mineralization is established to be about 1965 ± 25 million years.

scholarly journals Robotic grasp detection using a novel two-stage approach

2021 ◽  
Vol 1 (1) ◽  
pp. 19-29
Author(s):  
Zhe Chu ◽  
Mengkai Hu ◽  
Xiangyu Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Particle Swarm Optimizer ◽  
Neural Network Models ◽  
Two Stage ◽  
The Neural Network ◽  
End To End ◽  
Small Change ◽  
Robotic Grasp

Recently, deep learning has been successfully applied to robotic grasp detection. Based on convolutional neural networks (CNNs), there have been lots of end-to-end detection approaches. But end-to-end approaches have strict requirements for the dataset used for training the neural network models and it’s hard to achieve in practical use. Therefore, we proposed a two-stage approach using particle swarm optimizer (PSO) candidate estimator and CNN to detect the most likely grasp. Our approach achieved an accuracy of 92.8% on the Cornell Grasp Dataset, which leaped into the front ranks of the existing approaches and is able to run at real-time speeds. After a small change of the approach, we can predict multiple grasps per object in the meantime so that an object can be grasped in a variety of ways.

scholarly journals Commonsense Reasoning to Guide Deep Learning for Scene Understanding (Extended Abstract)

2020 ◽  
Author(s):  
Mohan Sridharan ◽  
Tiago Mota
Keyword(s):  
Domain Knowledge ◽  
Inductive Learning ◽  
Network Models ◽  
Computational Effort ◽  
Partial Occlusion ◽  
Commonsense Reasoning ◽  
Deep Networks ◽  
Training Examples ◽  
The Stability ◽  
Simulated Images

Our architecture uses non-monotonic logical reasoning with incomplete commonsense domain knowledge, and incremental inductive learning, to guide the construction of deep network models from a small number of training examples. Experimental results in the context of a robot reasoning about the partial occlusion of objects and the stability of object configurations in simulated images indicate an improvement in reliability and a reduction in computational effort in comparison with an architecture based just on deep networks.

Proper Boundary Conditions for Infinitely Layered Orthotropic Media

2000 ◽  
Vol 67 (3) ◽  
pp. 629-632
Author(s):  
E. L. Bonnaud ◽  
J. M. Neumeister
Keyword(s):  
Boundary Conditions ◽  
Layered Medium ◽  
Integral Transforms ◽  
Numerical Treatment ◽  
Problem Size ◽  
Transfer Matrix Approach ◽  
Stress Functions ◽  
Orthotropic Media ◽  
First Time ◽  
Conditions At Infinity

A stress analysis of a plane infinitely layered medium subjected to surface loadings is performed using Airy stress functions, integral transforms, and a revised transfer matrix approach. Proper boundary conditions at infinity are for the first time established, which reduces the problem size by one half. Methods and approximations are also presented to enable numerical treatment and to overcome difficulties inherent to such formulations. [S0021-8936(00)01103-X]

scholarly journals Data-to-Text Generation with Content Selection and Planning

2019 ◽  
Vol 33 ◽  
pp. 6908-6915 ◽  
Author(s):  
Ratish Puduppully ◽  
Li Dong ◽  
Mirella Lapata
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Network Models ◽  
Text Generation ◽  
Neural Network Models ◽  
Generation Task ◽  
Content Selection ◽  
End To End ◽  
Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

scholarly journals Image Shadow Removal Using End-to-End Deep Convolutional Neural Networks

2019 ◽  
Vol 9 (5) ◽  
pp. 1009 ◽  
Author(s):  
Hui Fan ◽  
Meng Han ◽  
Jinjiang Li
Keyword(s):  
Signal To Noise Ratio ◽  
Network Models ◽  
Structural Similarity ◽  
Shadow Removal ◽  
Deep Convolutional Neural Networks ◽  
Edge Information ◽  
Qualitative And Quantitative ◽  
Automatic Methods ◽  
End To End ◽  
High Level

Image degradation caused by shadows is likely to cause technological issues in image segmentation and target recognition. In view of the existing shadow removal methods, there are problems such as small and trivial shadow processing, the scarcity of end-to-end automatic methods, the neglecting of light, and high-level semantic information such as materials. An end-to-end deep convolutional neural network is proposed to further improve the image shadow removal effect. The network mainly consists of two network models, an encoder–decoder network and a small refinement network. The former predicts the alpha shadow scale factor, and the latter refines to obtain sharper edge information. In addition, a new image database (remove shadow database, RSDB) is constructed; and qualitative and quantitative evaluations are made on databases such as UIUC, UCF and newly-created databases (RSDB) with various real images. Using the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) for quantitative analysis, the algorithm has a big improvement on the PSNR and the SSIM as opposed to other methods. In terms of qualitative comparisons, the network shadow has a clearer and shadow-free image that is consistent with the original image color and texture, and the detail processing effect is much better. The experimental results show that the proposed algorithm is superior to other algorithms, and it is more robust in subjective vision and objective quantization.

Sign in / Sign up

Export Citation Format

Share Document