Latest YouTube Video
Saturday, November 21, 2015
Ocean City, MD's surf is at least 6.84ft high
Ocean City, MD Summary
At 2:00 AM, surf min of 2.48ft. At 8:00 AM, surf min of 4.66ft. At 2:00 PM, surf min of 6.84ft. At 8:00 PM, surf min of 7.93ft.
Surf maximum: 8.17ft (2.49m)
Surf minimum: 6.84ft (2.08m)
Tide height: -0.36ft (-0.11m)
Wind direction: E
Wind speed: 7.56 KTS
from Surfline http://ift.tt/1kVmigH
via IFTTT
Anonymous Hacking Group Takes Down 20,000 ISIS Twitter accounts
from The Hacker News http://ift.tt/1jcOsGS
via IFTTT
Salesforce ROI case study: Anonymous
from Google Alert - anonymous http://ift.tt/1laMQ1N
via IFTTT
Evil ISIS threatens revenge attack on hacking group Anonymous with shocking message
from Google Alert - anonymous http://ift.tt/1LrUPga
via IFTTT
Leonids and Friends
Friday, November 20, 2015
CISAC Cybersecurity Expert Analyzes Anonymous' Hacking Attacks on ISIS
from Google Alert - anonymous http://ift.tt/1O8lYuS
via IFTTT
Anonymous HIV Testing
from Google Alert - anonymous http://ift.tt/1SaeneE
via IFTTT
I have a new follower on Twitter
Secure Internet
This is the digital magazine of Byelex, It will bring you all the latest news and rumours regarding digital security on the Web. Data retreived via BuzzTalk
Netherlands
http://t.co/B8Vd6zJder
Following: 3117 - Followers: 9287
November 20, 2015 at 06:30PM via Twitter http://twitter.com/InetSecure
This Malware Can Secretly Auto-Install any Android App to Your Phone
from The Hacker News http://ift.tt/1kKWCYU
via IFTTT
Anonymous Recruiting You for War Against ISIS
from Google Alert - anonymous http://ift.tt/1MZHykn
via IFTTT
ISS Daily Summary Report – 11/19/15
from ISS On-Orbit Status Report http://ift.tt/1MrgitG
via IFTTT
Anonymous are now 'rickrolling' Isis
from Google Alert - anonymous http://ift.tt/1Yk9naV
via IFTTT
I have a new follower on Twitter
Doug Mesecar
edtech and edpolicy; public and private edu-perience (https://t.co/mf1Byyk5DK); blogger at http://t.co/8nRLLamjJr; son, dad, husband, mtn biker
NoVa
http://t.co/tXb8sEVa8Q
Following: 538 - Followers: 665
November 20, 2015 at 06:43AM via Twitter http://twitter.com/dmes
I have a new follower on Twitter
Lumina Analytics
Risk Identification & Risk Management to Corporate & Government Clients WorldWide. We use #BigData Analytics to identify risks that may otherwise go unnoticed.
United States
http://t.co/5bYh4R7Kid
Following: 1760 - Followers: 1742
November 20, 2015 at 03:28AM via Twitter http://twitter.com/LuminaAnalytics
Can Anonymous really accomplish something?
from Google Alert - anonymous http://ift.tt/1ly00Gv
via IFTTT
I have a new follower on Twitter
Foundr Magazine
Digital magazine for young entrepreneurs showing you exactly what it takes to build a successful business. Get your FREE Branson Issue - http://t.co/UIKlS06Ubt
Melbourne, Victoria
http://t.co/wPZsj5ksVs
Following: 63441 - Followers: 70053
November 20, 2015 at 01:44AM via Twitter http://twitter.com/FoundrMag
Centaurus A
Thursday, November 19, 2015
Anonymous accuses Silicon Valley startup of assisting Islamic State online
from Google Alert - anonymous http://ift.tt/1QxiYK6
via IFTTT
BIRDNEST: Bayesian Inference for Ratings-Fraud Detection. (arXiv:1511.06030v1 [cs.AI])
Review fraud is a pervasive problem in online commerce, in which fraudulent sellers write or purchase fake reviews to manipulate perception of their products and services. Fake reviews are often detected based on several signs, including 1) they occur in short bursts of time; 2) fraudulent user accounts have skewed rating distributions. However, these may both be true in any given dataset. Hence, in this paper, we propose an approach for detecting fraudulent reviews which combines these 2 approaches in a principled manner, allowing successful detection even when one of these signs is not present. To combine these 2 approaches, we formulate our Bayesian Inference for Rating Data (BIRD) model, a flexible Bayesian model of user rating behavior. Based on our model we formulate a likelihood-based suspiciousness metric, Normalized Expected Surprise Total (NEST). We propose a linear-time algorithm for performing Bayesian inference using our model and computing the metric. Experiments on real data show that BIRDNEST successfully spots review fraud in large, real-world graphs: the 50 most suspicious users of the Flipkart platform flagged by our algorithm were investigated and all identified as fraudulent by domain experts at Flipkart.
from cs.AI updates on arXiv.org http://ift.tt/1X1JcZz
via IFTTT
Putting Things in Context: Community-specific Embedding Projections for Sentiment Analysis. (arXiv:1511.06052v1 [cs.CL])
Variation in language is ubiquitous, and is particularly evident in newer forms of writing such as social media. Fortunately, variation is not random, but is usually linked to social factors. By exploiting linguistic homophily --- the tendency of socially linked individuals to use language similarly --- it is possible to build models that are more robust to variation. In this paper, we focus on social network communities, which make it possible to generalize sociolinguistic properties from authors in the training set to authors in the test sets, without requiring demographic author metadata. We detect communities via standard graph clustering algorithms, and then exploit these communities by learning community-specific projections of word embeddings. These projections capture shifts in word meaning in different social groups; by modeling them, we are able to improve the overall accuracy of Twitter sentiment analysis by a significant margin over competitive prior work.
from cs.AI updates on arXiv.org http://ift.tt/1kJ97UX
via IFTTT
Abstract Attribute Exploration with Partial Object Descriptions. (arXiv:1511.06191v1 [cs.AI])
Attribute exploration has been investigated in several studies, with particular emphasis on the algorithmic aspects of this knowledge acquisition method. In its basic version the method itself is rather simple and transparent. But when background knowledge and partially described counter-examples are admitted, it gets more difficult. Here we discuss this case in an abstract, somewhat "axiomatic" setting, providing a terminology that clarifies the abstract strategy of the method rather than its algorithmic implementation.
from cs.AI updates on arXiv.org http://ift.tt/1X1JzmX
via IFTTT
Teaching Machines to Read and Comprehend. (arXiv:1506.03340v3 [cs.CL] UPDATED)
Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.
from cs.AI updates on arXiv.org http://ift.tt/1F9CCkt
via IFTTT
Recurrent Reinforcement Learning: A Hybrid Approach. (arXiv:1509.03044v2 [cs.LG] UPDATED)
Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's entire interaction history and may require substantial domain knowledge. In this work, we investigate a deep-learning approach to learning the representation of states in partially observable tasks, with minimal prior knowledge of the domain. In particular, we propose a new family of hybrid models that combines the strength of both supervised learning (SL) and reinforcement learning (RL), trained in a joint fashion: The SL component can be a recurrent neural networks (RNN) or its long short-term memory (LSTM) version, which is equipped with the desired property of being able to capture long-term dependency on history, thus providing an effective way of learning the representation of hidden states. The RL component is a deep Q-network (DQN) that learns to optimize the control for maximizing long-term rewards. Extensive experiments in a direct mailing campaign problem demonstrate the effectiveness and advantages of the proposed approach, which performs the best among a set of previous state-of-the-art methods.
from cs.AI updates on arXiv.org http://ift.tt/1Q4VUP8
via IFTTT
[FD] Qualsoft Systems - (AddNewsDetails.php) Auth ByPass Vulnerability
Source: Gmail -> IFTTT-> Blogger
Re: [FD] LiteCart 1.3.2: Multiple XSS
Source: Gmail -> IFTTT-> Blogger
[FD] [CFP] No Big Thing Conference #2 San Francisco, December 5 2015
Source: Gmail -> IFTTT-> Blogger
[FD] LinkedIn - Persistent Cross-Site Scripting vulnerability(XSS)
Source: Gmail -> IFTTT-> Blogger
30 comments
from Google Alert - anonymous http://ift.tt/1Xcg64u
via IFTTT
EU clamps down on bitcoin, anonymous payments to curb terrorism funding
from Google Alert - anonymous http://ift.tt/1OhGZ4w
via IFTTT
VirusTotal now Scans Mac OS X Apps for Malware
from The Hacker News http://ift.tt/1PPOvpd
via IFTTT
What can Anonymous really do to ISIS?
from Google Alert - anonymous http://ift.tt/215mKy7
via IFTTT
Mark Zuckerberg Just Quits his Job at Facebook — Check Yourself!
from The Hacker News http://ift.tt/1PBMXR0
via IFTTT
ISS Daily Summary Report – 11/18/15
from ISS On-Orbit Status Report http://ift.tt/1Lo3v7l
via IFTTT
Is Telegram Really Secure? — 4 Major Privacy Issues Raised by Researcher
from The Hacker News http://ift.tt/1SGYtYZ
via IFTTT
Telegram — Secret Messaging app — Shuts Down 78 ISIS Channels
from The Hacker News http://ift.tt/1Moss6r
via IFTTT
A Sudden Jet on Comet 67P
Wednesday, November 18, 2015
A New Smooth Approximation to the Zero One Loss with a Probabilistic Interpretation. (arXiv:1511.05643v1 [cs.CV])
We examine a new form of smooth approximation to the zero one loss in which learning is performed using a reformulation of the widely used logistic function. Our approach is based on using the posterior mean of a novel generalized Beta-Bernoulli formulation. This leads to a generalized logistic function that approximates the zero one loss, but retains a probabilistic formulation conferring a number of useful properties. The approach is easily generalized to kernel logistic regression and easily integrated into methods for structured prediction. We present experiments in which we learn such models using an optimization method consisting of a combination of gradient descent and coordinate descent using localized grid search so as to escape from local minima. Our experiments indicate that optimization quality is improved when learning meta-parameters are themselves optimized using a validation set. Our experiments show improved performance relative to widely used logistic and hinge loss methods on a wide variety of problems ranging from standard UC Irvine and libSVM evaluation datasets to product review predictions and a visual information extraction task. We observe that the approach: 1) is more robust to outliers compared to the logistic and hinge losses; 2) outperforms comparable logistic and max margin models on larger scale benchmark problems; 3) when combined with Gaussian- Laplacian mixture prior on parameters the kernelized version of our formulation yields sparser solutions than Support Vector Machine classifiers; and 4) when integrated into a probabilistic structured prediction technique our approach provides more accurate probabilities yielding improved inference and increasing information extraction performance.
from cs.AI updates on arXiv.org http://ift.tt/1QOfyC2
via IFTTT
Discovering Underlying Plans Based on Distributed Representations of Actions. (arXiv:1511.05662v1 [cs.AI])
Plan recognition aims to discover target plans (i.e., sequences of actions) behind observed actions, with history plan libraries or domain models in hand. Previous approaches either discover plans by maximally "matching" observed actions to plan libraries, assuming target plans are from plan libraries, or infer plans by executing domain models to best explain the observed actions, assuming complete domain models are available. In real world applications, however, target plans are often not from plan libraries and complete domain models are often not available, since building complete sets of plans and complete domain models are often difficult or expensive. In this paper we view plan libraries as corpora and learn vector representations of actions using the corpora; we then discover target plans based on the vector representations. Our approach is capable of discovering underlying plans that are not from plan libraries, without requiring domain models provided. We empirically demonstrate the effectiveness of our approach by comparing its performance to traditional plan recognition approaches in three planning domains.
from cs.AI updates on arXiv.org http://ift.tt/1QOfwKp
via IFTTT
Using Abduction in Markov Logic Networks for Root Cause Analysis. (arXiv:1511.05719v1 [cs.AI])
IT infrastructure is a crucial part in most of today's business operations. High availability and reliability, and short response times to outages are essential. Thus a high amount of tool support and automation in risk management is desirable to decrease outages. We propose a new approach for calculating the root cause for an observed failure in an IT infrastructure. Our approach is based on Abduction in Markov Logic Networks. Abduction aims to find an explanation for a given observation in the light of some background knowledge. In failure diagnosis, the explanation corresponds to the root cause, the observation to the failure of a component, and the background knowledge to the dependency graph extended by potential risks. We apply a method to extend a Markov Logic Network in order to conduct abductive reasoning, which is not naturally supported in this formalism. Our approach exhibits a high amount of reusability and enables users without specific knowledge of a concrete infrastructure to gain viable insights in the case of an incident. We implemented the method in a tool and illustrate its suitability for root cause analysis by applying it to a sample scenario.
from cs.AI updates on arXiv.org http://ift.tt/1NEuk94
via IFTTT
Solution Repair/Recovery in Uncertain Optimization Environment. (arXiv:1511.05749v1 [cs.AI])
Operation management problems (such as Production Planning and Scheduling) are represented and formulated as optimization models. The resolution of such optimization models leads to solutions which have to be operated in an organization. However, the conditions under which the optimal solution is obtained rarely correspond exactly to the conditions under which the solution will be operated in the organization.Therefore, in most practical contexts, the computed optimal solution is not anymore optimal under the conditions in which it is operated. Indeed, it can be "far from optimal" or even not feasible. For different reasons, we hadn't the possibility to completely re-optimize the existing solution or plan. As a consequence, it is necessary to look for "repair solutions", i.e., solutions that have a good behavior with respect to possible scenarios, or with respect to uncertainty of the parameters of the model. To tackle the problem, the computed solution should be such that it is possible to "repair" it through a local re-optimization guided by the user or through a limited change aiming at minimizing the impact of taking into consideration the scenarios.
from cs.AI updates on arXiv.org http://ift.tt/1QOfyBO
via IFTTT
Alternative Markov Properties for Acyclic Directed Mixed Graphs. (arXiv:1511.05835v1 [stat.ML])
We extend AMP chain graphs by (i) relaxing the semidirected acyclity constraint so that only directed cycles are forbidden, and (ii) allowing up to two edges between any pair of nodes. We introduce global, ordered local and pairwise Markov properties for the new models. We show the equivalence of these properties for strictly positive probability distributions. We also show that, when the random variables are normally distributed, the new models can be interpreted as systems of linear equations with correlated errors. Finally, we describe an exact algorithm for learning the new models via answer set programming.
from cs.AI updates on arXiv.org http://ift.tt/1OfZpCV
via IFTTT
Behavior Query Discovery in System-Generated Temporal Graphs. (arXiv:1511.05911v1 [cs.SI])
Computer system monitoring generates huge amounts of logs that record the interaction of system entities. How to query such data to better understand system behaviors and identify potential system risks and malicious behaviors becomes a challenging task for system administrators due to the dynamics and heterogeneity of the data. System monitoring data are essentially heterogeneous temporal graphs with nodes being system entities and edges being their interactions over time. Given the complexity of such graphs, it becomes time-consuming for system administrators to manually formulate useful queries in order to examine abnormal activities, attacks, and vulnerabilities in computer systems.
In this work, we investigate how to query temporal graphs and treat query formulation as a discriminative temporal graph pattern mining problem. We introduce TGMiner to mine discriminative patterns from system logs, and these patterns can be taken as templates for building more complex queries. TGMiner leverages temporal information in graphs to prune graph patterns that share similar growth trend without compromising pattern quality. Experimental results on real system data show that TGMiner is 6-32 times faster than baseline methods. The discovered patterns were verified by system experts; they achieved high precision (97%) and recall (91%).
from cs.AI updates on arXiv.org http://ift.tt/1HZF3sU
via IFTTT
Factorization, Inference and Parameter Learning in Discrete AMP Chain Graphs. (arXiv:1501.06727v2 [stat.ML] UPDATED)
We address some computational issues that may hinder the use of AMP chain graphs in practice. Specifically, we show how a discrete probability distribution that satisfies all the independencies represented by an AMP chain graph factorizes according to it. We show how this factorization makes it possible to perform inference and parameter learning efficiently, by adapting existing algorithms for Markov and Bayesian networks. Finally, we turn our attention to another issue that may hinder the use of AMP CGs, namely the lack of an intuitive interpretation of their edges. We provide one such interpretation.
from cs.AI updates on arXiv.org http://ift.tt/1v0XrR6
via IFTTT
Managing Multi-Granular Linguistic Distribution Assessments in Large-Scale Multi-Attribute Group Decision Making. (arXiv:1504.01004v2 [cs.AI] UPDATED)
Linguistic large-scale group decision making (LGDM) problems are more and more common nowadays. In such problems a large group of decision makers are involved in the decision process and elicit linguistic information that are usually assessed in different linguistic scales with diverse granularity because of decision makers' distinct knowledge and background. To keep maximum information in initial stages of the linguistic LGDM problems, the use of multi-granular linguistic distribution assessments seems a suitable choice, however to manage such multigranular linguistic distribution assessments, it is necessary the development of a new linguistic computational approach. In this paper it is proposed a novel computational model based on the use of extended linguistic hierarchies, which not only can be used to operate with multi-granular linguistic distribution assessments, but also can provide interpretable linguistic results to decision makers. Based on this new linguistic computational model, an approach to linguistic large-scale multi-attribute group decision making is proposed and applied to a talent selection process in universities.
from cs.AI updates on arXiv.org http://ift.tt/1H0bxp7
via IFTTT
Anonymous releases guide on how to hack Isis
from Google Alert - anonymous http://ift.tt/1POgfKA
via IFTTT
I have a new follower on Twitter
GWEB Law
General practice law firm concentrating in the areas of Business, Civil Litigation, Personal Injury, Divorce, Family, Estate, Probate
Gaithersburg, MD
http://t.co/11KMAYysnO
Following: 2624 - Followers: 2402
November 18, 2015 at 03:31PM via Twitter http://twitter.com/gweblaw
Bob Ross Fans!
Friends of Bob Ross! Check out PBS NEWSHOUR’s article about one fan’s first experience with Bob Ross in ‘Here’s what happened when I tried to paint like Bob Ross’. Follow Link Below!
from The 'hotspot' for all things Bob Ross. http://ift.tt/1QuHImo
via IFTTT
Ravens: C Jeremy Zuttah (torn pectoral) placed on season-ending IR; 4th offensive player put on IR in the last 2 weeks (ESPN)
via IFTTT
New Pics Added to the Blog Gallery (November 18, 2015)
New Pics Added to the Blog Gallery! (November 18, 2015)
Click link below to visit gallery now!
http://ift.tt/1HAGoHC
from The 'hotspot' for all things Bob Ross. http://ift.tt/212vsNG
via IFTTT
ISS Daily Summary Report – 11/17/15
from ISS On-Orbit Status Report http://ift.tt/1S45qn3
via IFTTT
Hey ISIS! Check Out How 'Idiot' Anonymous Hackers Can Disrupt your Online Propaganda
from The Hacker News http://ift.tt/1lum0C4
via IFTTT
Google’s $85 Chromebit Lets You Turn Any Monitor or TV into a Computer
from The Hacker News http://ift.tt/1NaHn7M
via IFTTT
The Pelican Nebula in Gas Dust and Stars
Tuesday, November 17, 2015
I have a new follower on Twitter
Suzanne A Pierce
Science-informed Adaptation | Participatory Modeling | Intelligent Systems for Geosciences | Groundwater | Sustainability | Research | Crowdfunding | HCI Fan
Austin, TX & Calama, Chile
http://t.co/Kzfjd4LiS6
Following: 2109 - Followers: 2644
November 17, 2015 at 09:38PM via Twitter http://twitter.com/HelpfulTangent
Convolutional Models for Joint Object Categorization and Pose Estimation. (arXiv:1511.05175v1 [cs.CV])
In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable of capturing pose information over different categories of objects. With the rise of deep architectures, the prime focus has been on object category recognition. Deep learning methods have achieved wide success in this task. In contrast, object pose regression using these approaches has received relatively much less attention. In this paper we show how deep architectures, specifically Convolutional Neural Networks (CNN), can be adapted to the task of simultaneous categorization and pose estimation of objects. We investigate and analyze the layers of various CNN models and extensively compare between them with the goal of discovering how the layers of distributed representations of CNNs represent object pose information and how this contradicts with object category representations. We extensively experiment on two recent large and challenging multi-view datasets. Our models achieve better than state-of-the-art performance on both datasets.
from cs.AI updates on arXiv.org http://ift.tt/1WY53kr
via IFTTT
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering. (arXiv:1511.05234v1 [cs.CV])
The problem of Visual Question Answering (VQA) requires joint image and language understanding to answer a question about a given photograph. Recent approaches have applied deep image captioning methods based on recurrent LSTM networks to this problem, but have failed to model spatial inference. In this paper, we propose a memory network with spatial attention for the VQA task. Memory networks are recurrent neural networks with an explicit attention mechanism that selects certain parts of the information stored in memory. We store neuron activations from different spatial receptive fields in the memory, and use the question to choose relevant regions for computing the answer. We experiment with spatial attention architectures that use different question representations to choose regions, and also show that two attention steps (hops) obtain improved results compared to a single step. To understand the inference process learned by the network, we design synthetic questions that specifically require spatial inference and visualize the attention weights. We evaluate our model on two published visual question answering datasets, DAQUAR and VQA, and obtain promising results.
from cs.AI updates on arXiv.org http://ift.tt/1MlcR7C
via IFTTT
Constant Time EXPected Similarity Estimation using Stochastic Optimization. (arXiv:1511.05371v1 [cs.LG])
A new algorithm named EXPected Similarity Estimation (EXPoSE) was recently proposed to solve the problem of large-scale anomaly detection. It is a non-parametric and distribution free kernel method based on the Hilbert space embedding of probability measures. Given a dataset of $n$ samples, EXPoSE needs only $\mathcal{O}(n)$ (linear time) to build a model and $\mathcal{O}(1)$ (constant time) to make a prediction. In this work we improve the linear computational complexity and show that an $\epsilon$-accurate model can be estimated in constant time, which has significant implications for large-scale learning problems. To achieve this goal, we cast the original EXPoSE formulation into a stochastic optimization problem. It is crucial that this approach allows us to determine the number of iteration based on a desired accuracy $\epsilon$, independent of the dataset size $n$. We will show that the proposed stochastic gradient descent algorithm works in general (possible infinite-dimensional) Hilbert spaces, is easy to implement and requires no additional step-size parameters.
from cs.AI updates on arXiv.org http://ift.tt/1WY54oE
via IFTTT
Active exploration of sensor networks from a robotics perspective. (arXiv:1511.05488v1 [cs.RO])
Traditional algorithms for robots who need to integrate into a wireless network often focus on one specific task. In this work we want to develop simple, adaptive and reusable algorithms for real world applications for this scenario. Starting with the most basic task for mobile wireless network nodes, finding the position of another node, we introduce an algorithm able to solve this task. We then show how this algorithm can readily be employed to solve a large number of other related tasks like finding the optimal position to bridge two static network nodes. For this we first introduce a meta-algorithm inspired by autonomous robot learning strategies and the concept of internal models which yields a class of source seeking algorithms for mobile nodes. The effectiveness of this algorithm is demonstrated in real world experiments using a physical mobile robot and standard 802.11 wireless LAN in an office environment. We also discuss the differences to conventional algorithms and give the robotics perspective on this class of algorithms. Then we proceed to show how more complex tasks, which might be encountered by mobile nodes, can be encoded in the same framework and how the introduced algorithm can solve them. These tasks can be direct (cross layer) optimization tasks or can also encode more complex tasks like bridging two network nodes. We choose the bridging scenario as an example, implemented on a real physical robot, and show how the robot can solve it in a real world experiment.
from cs.AI updates on arXiv.org http://ift.tt/1MlcQRj
via IFTTT
Gated Graph Sequence Neural Networks. (arXiv:1511.05493v1 [cs.LG])
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then extend to output sequences. The result is a flexible and broadly useful class of neural network models that has favorable inductive biases relative to purely sequence-based models (e.g., LSTMs) when the problem is graph-structured. We demonstrate the capabilities on some simple AI (bAbI) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.
from cs.AI updates on arXiv.org http://ift.tt/1HXcQTm
via IFTTT
Neurocontrol methods review. (arXiv:1511.05506v1 [cs.AI])
Methods of applying neural networks to control plants are considered. Methods and schemes are described, their advantages and disadvantages are discussed.
from cs.AI updates on arXiv.org http://ift.tt/1WY53kl
via IFTTT
Return of Frustratingly Easy Domain Adaptation. (arXiv:1511.05547v1 [cs.CV])
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being ``frustratingly easy'' to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation. We propose a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. Even though it is extraordinarily simple--it can be implemented in four lines of Matlab code--CORAL performs remarkably well in extensive evaluations on standard benchmark datasets.
from cs.AI updates on arXiv.org http://ift.tt/1WY5345
via IFTTT
A state vector algebra for algorithmic implementation of second-order logic. (arXiv:1312.2551v2 [cs.AI] UPDATED)
We present a mathematical framework for mapping second-order logic relations onto a simple state vector algebra. Using this algebra, basic theorems of set theory can be proven in an algorithmic way, hence by an expert system. We illustrate the use of the algebra with simple examples and show that, in principle, all theorems of basic set theory can be recovered in an elementary way. The developed technique can be used for an automated theorem proving in the 1st and 2nd order logic.
from cs.AI updates on arXiv.org http://ift.tt/19xG6i0
via IFTTT
Ethical Artificial Intelligence. (arXiv:1411.1373v9 [cs.AI] UPDATED)
This book-length article combines several peer reviewed papers and new material to analyze the issues of ethical artificial intelligence (AI). The behavior of future AI systems can be described by mathematical equations, which are adapted to analyze possible unintended AI behaviors and ways that AI designs can avoid them. This article makes the case for utility-maximizing agents and for avoiding infinite sets in agent definitions. It shows how to avoid agent self-delusion using model-based utility functions and how to avoid agents that corrupt their reward generators (sometimes called "perverse instantiation") using utility functions that evaluate outcomes at one point in time from the perspective of humans at a different point in time. It argues that agents can avoid unintended instrumental actions (sometimes called "basic AI drives" or "instrumental goals") by accurately learning human values. This article defines a self-modeling agent framework and shows how it can avoid problems of resource limits, being predicted by other agents, and inconsistency between the agent's utility function and its definition (one version of this problem is sometimes called "motivated value selection"). This article also discusses how future AI will differ from current AI, the politics of AI, and the ultimate use of AI to help understand the nature of the universe and our place in it.
from cs.AI updates on arXiv.org http://ift.tt/1uxUvdS
via IFTTT
Computing rational decisions in extensive games with limited foresight. (arXiv:1502.03683v3 [cs.AI] UPDATED)
We introduce a class of extensive form games where players might not be able to foresee the possible consequences of their decisions and form a model of their opponents which they exploit to achieve a more profitable outcome. We improve upon existing models of games with limited foresight, endowing players with the ability of higher-order reasoning and proposing a novel solution concept to address intuitions coming from real game play. We analyse the resulting equilibria, devising an effective procedure to compute them.
from cs.AI updates on arXiv.org http://ift.tt/1D1Dwnu
via IFTTT
I have a new follower on Twitter
Claudia Hilker
#Consulting #Digital #Business #Transformation #SocialMedia #Content #Marketing #Kommunikation #Blogger #Management #Speaker #Autor
Germany, Düsseldorf
https://t.co/x93lOhwAdy
Following: 2060 - Followers: 6332
November 17, 2015 at 05:38PM via Twitter http://twitter.com/claudiahilker
[FD] zTree v3 Security Advisory - XSS Vulnerability - CVE-2015-7348
Source: Gmail -> IFTTT-> Blogger
[FD] CVE-2015-6357: Cisco FireSIGHT Management Center SSL Validation Vulnerability
Source: Gmail -> IFTTT-> Blogger
Ravens: WR Breshad Perriman (1st-round pick); placed on season ending IR with knee injury; did not appear in any games (ESPN)
via IFTTT
Anonymous Declares War on ISIS, Takes Down 5500 Twitter Accounts
from Google Alert - anonymous http://ift.tt/1ltoz7z
via IFTTT
Ravens: Baltimore (2-7) drops five spots to No. 29 in Week 11 NFL power rankings; open here for full rankings (ESPN)
via IFTTT
Anonymous hackers declare war on IS
from Google Alert - anonymous http://ift.tt/1QsLH2A
via IFTTT
I have a new follower on Twitter
Robyn Wyrick
Novelist, author of Eviction Notice Screenwriter Owner of DC PHP, LLC Owner of Anticipation Films Founder of the Washington DC PHP Developers Group
Nanjemoy, MD
http://t.co/Pg3PdxaLA6
Following: 77 - Followers: 45
November 17, 2015 at 12:22PM via Twitter http://twitter.com/robynwyrick
ISIS Calls Anonymous "IDIOTS" and Issues 5 Lame Tips for its Members to Avoid Getting Hacked
from The Hacker News http://ift.tt/1X522JX
via IFTTT
Ravens: Ex-Baltimore DT Terrence Cody convicted of misdemeanors in animal abuse case (ESPN)
via IFTTT
I have a new follower on Twitter
SOCIAL OUTLIER
If Ms. Digital Marketing went on a date with Mr. Calculus...we are the offspring. Our approach to digital marketing is entirely mathematically optimized!
Los Angeles, CA
https://t.co/eXB9qeo29h
Following: 3266 - Followers: 3501
November 17, 2015 at 09:40AM via Twitter http://twitter.com/SocialOutlier
SS Daily Summary Report – 11/16/15
from ISS On-Orbit Status Report http://ift.tt/1l2sJCX
via IFTTT
[FD] Free WMA MP3 Converter - Buffer Overflow Exploit (SEH)
Source: Gmail -> IFTTT-> Blogger
[FD] Murgent CMS - SQL Injection Vulnerability
Source: Gmail -> IFTTT-> Blogger
[FD] LineNity WP Premium Theme - File Include Vulnerability
Source: Gmail -> IFTTT-> Blogger
Anonymous has made its first 'cyber attack' on Isis
from Google Alert - anonymous http://ift.tt/1OOrHaL
via IFTTT
Would Encryption Backdoor Stop Paris-like Terror Attacks?
from The Hacker News http://ift.tt/1kC3FD2
via IFTTT