"We've been using it for sheep, pigs and cows," said Zhao Jinshi, who studied at Cornell University and founded Beijing Unitrace Tech, a company developing software for the agriculture industry. "For pigs, it's more difficult because pigs all look the same, but dairy cows are a bit special because they are black and white and have different shapes," Zhao said as he checked on the technology installed in a pilot project here at a farm in Hebei province, outside Beijing. China has led the world in developing facial recognition capabilities. There are almost 630 million facial recognition cameras in use in the country, for security purposes as well as for everyday conveniences like entering train stations and paying for goods in stores. But authorities also use the technology for sinister means, such as monitoring political dissidents and ethnic minorities.

In this paper we discuss the relationships between conditional and preferential logics and neural network models, based on a multi-preferential semantics. We propose a concept-wise multipreference semantics, recently introduced for defeasible description logics to take into account preferences with respect to different concepts, as a tool for providing a semantic interpretation to neural network models. This approach has been explored both for unsupervised neural network models (Self-Organising Maps) and for supervised ones (Multilayer Perceptrons), and we expect that the same approach might be extended to other neural network models. It allows for logical properties of the network to be checked (by model checking) over an interpretation capturing the input-output behavior of the network. For Multilayer Perceptrons, the deep network itself can be regarded as a conditional knowledge base, in which synaptic connections correspond to weighted conditionals. The paper describes the general approach, through the cases of Self-Organising Maps and Multilayer Perceptrons, and discusses some open issues and perspectives.

Social-aware recommendation approaches have been recognized as an effective way to solve the data sparsity issue of traditional recommender systems. The assumption behind is that the knowledge in social user-user connections can be shared and transferred to the domain of user-item interactions, whereby to help learn user preferences. However, most existing approaches merely adopt the first-order connections among users during transfer learning, ignoring those connections in higher orders. We argue that better recommendation performance can also benefit from high-order social relations. In this paper, we propose a novel Propagation-aware Transfer Learning Network (PTLN) based on the propagation of social relations. We aim to better mine the sharing knowledge hidden in social networks and thus further improve recommendation performance. Specifically, we explore social influence in two aspects: (a) higher-order friends have been taken into consideration by order bias; (b) different friends in the same order will have distinct importance for recommendation by an attention mechanism. Besides, we design a novel regularization to bridge the gap between social relations and user-item interactions. We conduct extensive experiments on two real-world datasets and beat other counterparts in terms of ranking accuracy, especially for the cold-start users with few historical interactions.

It is beneficial to automate the process of deriving concept hierarchies from corpora since a manual construction of concept hierarchies is typically a time consuming and resource-intensive process. As such, the overall process of learning concept hierarchies from corpora encompasses a set of steps: parsing the text into sentences, splitting the sentences and then tokenised it. After the lemmatisation step, the pairs are extracted using formal context analysis (FCA). However, there might be some uninteresting and erroneous pairs in the formal context. Generating formal context may lead to a time-consuming process, so formal context size reduction is require to remove uninterested and erroneous pairs, taking less time to extract the concept lattice and concept hierarchies accordingly. In this premise, this study aims to propose two frameworks: i) A framework to review the current process of deriving concept hierarchies from corpus utilising formal concept analysis (FCA); ii) A framework to decrease the formal context's ambiguity of the first framework using an adaptive version of evolutionary clustering algorithm (ECA*). Experiments are conducted by applying 385 samples corpora from Wikipedia on the two frameworks to examine the reducing size of formal context, which leads to yield concept lattice and concept hierarchy. The resulting lattice of formal context is evaluated to the standad one using concept latticeinvariants. Accordingly, the homomorphic between the two lattices preserves the quality of resulting concept hierarchies by 89% in contrast to the basic ones, and the reduced concept lattice inherits the structural relation of the standard one. The adaptive ECA* is examined against its four counterpart baseline algorithms (Fuzzy K-means, JBOS approach, AddIntent algorithm, and FastAddExtent) to measure the execution time on random datasets with different densities (fill ratios). The results show that adaptive ECA* performs concept lattice faster than other mentioned competitive techniques in different fill ratios. Keywords Concept hierarchies, formal context reduction, concept lattice reduction, adaptive ECA*, FCA, WordNet. 1. Introduction The Semantic Web is an extended web of machine-readable data, which provides a program to process data via machine directly or indirectly [1]. As an expansion of the latest Web, the Semantic Web can add meaning to the World Wide Web content and thus support automated services on the basis os semantic representations. Meanwhile, the Semantic Web depends on structured ontologies to organize the underlying data and provide a detailed and portable interpretation of computing machines [2].

Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the potentially useful middle and high frequency band of graph signals are ignored. Second, the bandwidth of existing graph convolutional filters is fixed. Parameters of a graph convolutional filter only transform the graph inputs without changing the curvature of a graph convolutional filter function. In reality, we are uncertain about whether we should retain or cut off the frequency at a certain point unless we have expert domain knowledge. In this paper, we propose Automatic Graph Convolutional Networks (AutoGCN) to capture the full spectrum of graph signals and automatically update the bandwidth of graph convolutional filters. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form. Experimental results show that AutoGCN achieves significant improvement over baseline methods which only work as low-pass filters.

In this post, you learn how to create a MLOps project to automate the deployment of an Amazon SageMaker endpoint with multiple production variants for A/B testing. You also deploy a general purpose API and testing infrastructure that includes a multi-armed bandit experiment framework. This testing infrastructure will automatically optimize traffic to the best-performing model over time based on user feedback. Amazon SageMaker MLOps projects are a new capability recently released with Amazon SageMaker Pipelines, the first purpose-built, easy-to-use, continuous integration and continuous delivery (CI/CD) service for ML. The MLOps project template provisions the initial setup required for a complete end-to-end MLOps system, including model building, training, and deployment, and can be customized to support your own organizations requirements.

Retired Navy SEAL Commander Dave Sears suggests Russia, China and Pakistan could face national security issues once U.S. troops leave Afghanistan. This is a rush transcript of "Your World with Neil Cavuto" on July 8, 2021. This copy may not be in its final form and may be updated. QUESTION: Do you trust the Taliban, Mr. President? Do you trust the Taliban, sir? JOE BIDEN, PRESIDENT OF THE UNITED STATES: Are you -- is that a serious question? QUESTION: It is absolutely a serious question. Do you trust the Taliban? BIDEN: No, I do not. BIDEN: No, I do not trust the Taliban. QUESTION: Is the U.S. responsible for the deaths that happen the Afghans after you leave the country? QUESTION: Mr. President, will you amplify that question, please? Will you amplify your answer, please, why you don't trust the Taliban? BIDEN: It is a silly question. Do I trust the Taliban? And it almost seemed like a Donald Trump press conference, with angry reporters trying to get a simple answer from the president, and their agitation showing, as the questions and the nonanswers went on, all of this at a time U.S. forces are moving rapidly ahead of schedule. Better than 90 percent now have left Afghanistan. And we could see them all out well before the 9/11 deadline that the president has set. But he says he's not going to change his mind. And he says that, after 20 years, Afghans must look after themselves. Jennifer Griffin has more from the Pentagon.

You don't want your face to appear in the database of Clearview AI? The company's CEO doesn't seem to care. "All the information we collect is collected legally and it is all publicly available information," Hoan Ton-That said Monday during DW's Global Media Forum (GMF), addressing criticism that the firm's controversial technology infringes on the privacy of hundreds of millions. Privacy activists recently lodged data protection complaints against Clearview AI in five European countries. They argue that the software -- a search engine for faces combing through billions of photos -- violates the UK's and the EU's strict privacy rules.

Registrations are now open for the 5th World of Drones and Robotics Congress (WoDaRC), which will be held at the Brisbane Convention & Exhibition Centre, 18 -19 August 2021. WoDaRC will again be presented as a live physical congress for those who can attend with virtual options for those who cannot. Exhibitors now have the option of lower-cost display "pods" in a new exhibition area which will include networking spaces and food service. Virtual exhibits will also be available. Attend, network, speak, exhibit or watch WoDaRC in the manner that best suits you.

Deep Neural Networks (DNN) are known to be vulnerable to adversarial samples, the detection of which is crucial for the wide application of these DNN models. Recently, a number of deep testing methods in software engineering were proposed to find the vulnerability of DNN systems, and one of them, i.e., Model Mutation Testing (MMT), was used to successfully detect various adversarial samples generated by different kinds of adversarial attacks. However, the mutated models in MMT are always huge in number (e.g., over 100 models) and lack diversity (e.g., can be easily circumvented by high-confidence adversarial samples), which makes it less efficient in real applications and less effective in detecting high-confidence adversarial samples. In this study, we propose Graph-Guided Testing (GGT) for adversarial sample detection to overcome these aforementioned challenges. GGT generates pruned models with the guide of graph characteristics, each of them has only about 5% parameters of the mutated model in MMT, and graph guided models have higher diversity. The experiments on CIFAR10 and SVHN validate that GGT performs much better than MMT with respect to both effectiveness and efficiency.