scholarly journals End-to-End Game-Focused Learning of Adversary Behavior in Security Games

2020 ◽  
Vol 34 (02) ◽  
pp. 1378-1386
Author(s):  
Andrew Perrault ◽  
Bryan Wilder ◽  
Eric Ewing ◽  
Aditya Mate ◽  
Bistra Dilkina ◽  
...  
Keyword(s):  
Expected Utility ◽  
Optimization Problem ◽  
Predictive Accuracy ◽  
Experimental Results ◽  
Limited Data ◽  
Two Stage ◽  
Security Games ◽  
End To End ◽  
Feature Values ◽  
Adversary Model

Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary. Motivated by green security, where the defender may only observe an adversary's response to defense on a limited set of targets, we study the problem of learning a defense that generalizes well to a new set of targets with novel feature values and combinations. Traditionally, this problem has been addressed via a two-stage approach where an adversary model is trained to maximize predictive accuracy without considering the defender's optimization problem. We develop an end-to-end game-focused approach, where the adversary model is trained to maximize a surrogate for the defender's expected utility. We show both in theory and experimental results that our game-focused approach achieves higher defender expected utility than the two-stage alternative when there is limited data.

Local Graph Edge Partitioning

2021 ◽  
Vol 12 (5) ◽  
pp. 1-25
Author(s):  
Shengwei Ji ◽  
Chenyang Bu ◽  
Lei Li ◽  
Xindong Wu
Keyword(s):  
Real World ◽  
Graph Partitioning ◽  
Large Scale ◽  
Complete Information ◽  
Local Information ◽  
Experimental Results ◽  
Two Stage ◽  
Graph Computation ◽  
Local Graph ◽  
Edge Partitioning

Graph edge partitioning, which is essential for the efficiency of distributed graph computation systems, divides a graph into several balanced partitions within a given size to minimize the number of vertices to be cut. Existing graph partitioning models can be classified into two categories: offline and streaming graph partitioning models. The former requires global graph information during the partitioning, which is expensive in terms of time and memory for large-scale graphs. The latter creates partitions based solely on the received graph information. However, the streaming model may result in a lower partitioning quality compared with the offline model. Therefore, this study introduces a Local Graph Edge Partitioning model, which considers only the local information (i.e., a portion of a graph instead of the entire graph) during the partitioning. Considering only the local graph information is meaningful because acquiring complete information for large-scale graphs is expensive. Based on the Local Graph Edge Partitioning model, two local graph edge partitioning algorithms—Two-stage Local Partitioning and Adaptive Local Partitioning—are given. Experimental results obtained on 14 real-world graphs demonstrate that the proposed algorithms outperform rival algorithms in most tested cases. Furthermore, the proposed algorithms are proven to significantly improve the efficiency of the real graph computation system GraphX.

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 Consistency-Check Edge Refinement for Deep Stereo Matching

2020 ◽  
Author(s):  
Fangrui Wu ◽  
Menglong Yang
Keyword(s):  
Computational Efficiency ◽  
Stereo Matching ◽  
Information Aggregation ◽  
Experimental Results ◽  
Global Information ◽  
Consistency Check ◽  
Filtering Method ◽  
Tightly Coupled ◽  
End To End ◽  
Public Datasets

Recent end-to-end CNN-based stereo matching algorithms obtain disparities through regression from a cost volume, which is formed by concatenating the features of stereo pairs. Some downsampling steps are often embedded in constructing cost volume for global information aggregation and computational efficiency. However, many edge details are hard to recover due to the imprudent upsampling process and ambiguous boundary predictions. To tackle this problem without training another edge prediction sub-network, we developed a novel tightly-coupled edge refinement pipeline composed of two modules. The first module implements a gentle upsampling process by a cascaded cost volume filtering method, aggregating global information without losing many details. On this basis, the second module concentrates on generating a disparity residual map for boundary pixels by sub-pixel disparity consistency check, to further recover the edge details. The experimental results on public datasets demonstrate the effectiveness of the proposed method.

scholarly journals Towards High-Level Intrinsic Exploration in Reinforcement Learning

2020 ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Reinforcement Learning ◽  
Time Horizon ◽  
State Of The Art ◽  
Experimental Results ◽  
Prior Work ◽  
Extrinsic Rewards ◽  
Intrinsic Reward ◽  
Long Time ◽  
End To End ◽  
High Level

Deep reinforcement learning (DRL) methods traditionally struggle with tasks where environment rewards are sparse or delayed, which entails that exploration remains one of the key challenges of DRL. Instead of solely relying on extrinsic rewards, many state-of-the-art methods use intrinsic curiosity as exploration signal. While they hold promise of better local exploration, discovering global exploration strategies is beyond the reach of current methods. We propose a novel end-to-end intrinsic reward formulation that introduces high-level exploration in reinforcement learning. Our curiosity signal is driven by a fast reward that deals with local exploration and a slow reward that incentivizes long-time horizon exploration strategies. We formulate curiosity as the error in an agent’s ability to reconstruct the observations given their contexts. Experimental results show that this high-level exploration enables our agents to outperform prior work in several Atari games.

scholarly journals A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification

2018 ◽  
Author(s):  
Shuming Ma ◽  
Xu Sun ◽  
Junyang Lin ◽  
Xuancheng Ren
Keyword(s):  
Hierarchical Structure ◽  
Online Reviews ◽  
Text Summarization ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Joint Learning ◽  
End To End ◽  
Abstractive Summarization ◽  
Main Ideas ◽  
Different Levels

Text summarization and sentiment classification both aim to capture the main ideas of the text but at different levels. Text summarization is to describe the text within a few sentences, while sentiment classification can be regarded as a special type of summarization which ``summarizes'' the text into a even more abstract fashion, i.e., a sentiment class. Based on this idea, we propose a hierarchical end-to-end model for joint learning of text summarization and sentiment classification, where the sentiment classification label is treated as the further ``summarization'' of the text summarization output. Hence, the sentiment classification layer is put upon the text summarization layer, and a hierarchical structure is derived. Experimental results on Amazon online reviews datasets show that our model achieves better performance than the strong baseline systems on both abstractive summarization and sentiment classification.

scholarly journals Breakdown Detection in Negotiation Dialogues (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13969-13970
Author(s):  
Atsuki Yamaguchi ◽  
Katsuhide Fujita
Keyword(s):  
Artificial Intelligence ◽  
Natural Language ◽  
Language Model ◽  
Experimental Results ◽  
Conflicts Of Interests ◽  
Early Stages ◽  
End To End ◽  
Gated Recurrent Unit

In human-human negotiation, reaching a rational agreement can be difficult, and unfortunately, the negotiations sometimes break down because of conflicts of interests. If artificial intelligence can play a role in assisting with human-human negotiation, it can assist in avoiding negotiation breakdown, leading to a rational agreement. Therefore, this study focuses on end-to-end tasks for predicting the outcome of a negotiation dialogue in natural language. Our task is modeled using a gated recurrent unit and a pre-trained language model: BERT as the baseline. Experimental results demonstrate that the proposed tasks are feasible on two negotiation dialogue datasets, and that signs of a breakdown can be detected in the early stages using the baselines even if the models are used in a partial dialogue history.

Two Stage Mini-Max Algorithm for Grid-Based Wind Farm Layout Optimization

2017 ◽  
Author(s):  
Ning Quan ◽  
Harrison Kim
Keyword(s):  
Power Output ◽  
Wind Farm ◽  
Optimization Problem ◽  
Layout Optimization ◽  
Discrete Optimization Problem ◽  
Real World Data ◽  
Two Stage ◽  
Wind Farm Layout ◽  
Wind Farm Layout Optimization ◽  
Grid Based

The power maximizing grid-based wind farm layout optimization problem seeks to determine the layout of a given number of turbines from a grid of possible locations such that wind farm power output is maximized. The problem in general is a nonlinear discrete optimization problem which cannot be solved to optimality, so heuristics must be used. This article proposes a new two stage heuristic that first finds a layout that minimizes the maximum pairwise power loss between any pair of turbines. The initial layout is then changed one turbine at a time to decrease sum of pairwise power losses. The proposed heuristic is compared to the greedy algorithm using real world data collected from a site in Iowa. The results suggest that the proposed heuristic produces layouts with slightly higher power output, but are less robust to changes in the dominant wind direction.

scholarly journals Deep Colorization for Surveillance Images

2018 ◽  
Vol 228 ◽  
pp. 02009
Author(s):  
Chen Yao ◽  
Yan Xia
Keyword(s):  
Image Processing ◽  
Video Surveillance ◽  
Experimental Results ◽  
Grayscale Image ◽  
End To End ◽  
Surveillance Application

In video surveillance application, grayscale image often influences the image processing results. In order to solve the colorization problem for surveillance images, this paper propose a fully end-to-end approach to obtain a reasonable colorization results. A CNN learning structure and gradient prior are be used for chromatic space inferring. Finally, our experimental results show our advantage.

scholarly journals An Energy-Efficient Two-Stage Cooperative Routing Scheme in Wireless Multi-Hop Networks

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1002 ◽  
Author(s):  
Jianming Cheng ◽  
Yating Gao ◽  
Ningbo Zhang ◽  
Hongwen Yang
Keyword(s):  
Energy Efficiency ◽  
Network Lifetime ◽  
Cooperative Transmission ◽  
Transmission Model ◽  
Two Stage ◽  
Routing Scheme ◽  
Cooperative Routing ◽  
Link Cost ◽  
Simulation Results ◽  
End To End

Cooperative routing is one of the most widely used technologies for improving the energy efficiency and energy balance of wireless multi-hop networks. However, the end-to-end energy cost and network lifetime are greatly restricted if the cooperative transmission model is not designed properly. The main aim of this paper is to explore a two-stage cooperative routing scheme to further improve the energy efficiency and prolong the network lifetime. A two-stage cooperative (TSC) transmission model is firstly designed in which the core helper is introduced to determine the helper set for cooperation. Then, the two-stage link cost is formulated where x, the weight of residual energy, is introduced to be adjusted for different design goals. By selecting the optimal helper set, the two-stage link cost of each link can be optimized. Finally, based on the designed TSC transmission model and the optimized two-stage link cost, a distributed two-stage cooperative routing (TSCR) scheme is further proposed to minimize the end-to-end cooperative routing cost. Simulation results evaluate the effect of x on the different performance metrics. When x equals 0, TSCR can achieve the shortest end-to-end transmission delay and highest energy efficiency, while a larger x can achieve a longer network lifetime. Furthermore, simulation results also show that the proposed TSCR scheme can effectively improve both the energy efficiency and network lifetime compared with the existing schemes.

Sign in / Sign up

Export Citation Format

Share Document