Graph learning from data represents a canonical problem that has received substantial attention in the literature. However, insufficient work has been done in incorporating prior structural knowledge onto the learning of underlying graphical models from data. Learning a graph with a specific structure is essential for interpretability and identification of the relationships among data. Useful structured graphs include the multi-component graph, bipartite graph, connected graph, sparse graph, and regular graph. In general, structured graph learning is an NP-hard combinatorial problem, therefore, designing a general tractable optimization method is extremely challenging. In this paper, we introduce a unified graph learning framework lying at the integration of Gaussian graphical models and spectral graph theory. To impose a particular structure on a graph, we first show how to formulate the combinatorial constraints as an analytical property of the graph matrix. Then we develop an optimization framework that leverages graph learning with specific structures via spectral constraints on graph matrices. The proposed algorithms are provably convergent, computationally efficient, and practically amenable for numerous graph-based tasks. Extensive numerical experiments with both synthetic and real data sets illustrate the effectiveness of the proposed algorithms. The code for all the simulations is made available as an open source repository.

A pillar box red electric train connects Paris, Verona and Grenada via Budapest's Liberty Bridge and on to Heidelberg Castle in a 120-hectare fantasy business park dreamt up by the Chinese billionaire Ren Zhengfei. Ren, 74, a former Red Army engineer who founded the telecommunications company Huawei in 1987 and still owns a 1.14% stake, asked the Japanese architect Kengo Kuma to recreate some of Europe's most historic cities. He hoped to inspire an army of 25,000 research and development staff to challenge Apple, Google and Samsung. While its US competitors keep their research facilities on lockdown to prevent corporate espionage (oft allegedly by the Chinese), Huawei is inviting the world's media into its labs and factories in an attempt to dispel the US government's claims that the privately held company is an arm of the Chinese state and that its technology could be used to hack into western governments. US politicians allege that Huawei's forthcoming 5G mobile phone networks could be hacked by Chinese spies to eavesdrop on sensitive phone calls, gain access to counter-terrorist operations – and potentially even kill targets by crashing driverless cars.

Unsupervised relation discovery aims to discover new relations from a given text corpus without annotated data. However, it does not consider existing human annotated knowledge bases even when they are relevant to the relations to be discovered. In this paper, we study the problem of how to use out-of-relation knowledge bases to supervise the discovery of unseen relations, where out-of-relation means that relations to discover from the text corpus and those in knowledge bases are not overlapped. We construct a set of constraints between entity pairs based on the knowledge base embedding and then incorporate constraints into the relation discovery by a variational auto-encoder based algorithm. Experiments show that our new approach can improve the state-of-the-art relation discovery performance by a large margin.

RIO DE JANEIRO, BRAZIL – iFood is planning to invest US$20 million in opening an AI learning center to strengthen ties with the tech industry. With an expected staff of 100 people by the end of the year, everything from machine learning, deep learning, behavioral science, and logistics will be covered. All of this is part of iFood's US$500 million funding round that began last year. São Paulo-based iFood is one of Latin America's biggest and most successful startup food delivery company. Seeing how the international food delivery ecosystem is worth around US$94 billion, it's easy to understand why iFood takes digital innovations so seriously.

This paper introduces a novel approach for dengue fever classification based on online learning paradigms. The proposed approach is suitable for practical implementation as it enables learning using only a few training samples. With time, the proposed approach is capable of learning incrementally from the data collected without need for retraining the model or redeployment of the prediction engine. Additionally, we also provide a comprehensive evaluation of machine learning methods for prediction of dengue fever. The input to the proposed pipeline comprises of recorded patient symptoms and diagnostic investigations. Offline classifier models have been employed to obtain baseline scores to establish that the feature set is optimal for classification of dengue. The primary benefit of the online detection model presented in the paper is that it has been established to effectively identify patients with high likelihood of dengue disease, and experiments on scalability in terms of number of training and test samples validate the use of the proposed model.

Hundreds of human reviewers across the globe, from Romania to Venezuela, listen to audio clips recorded from Amazon Echo speakers, usually without owners' knowledge, Bloomberg reported last week. We knew Alexa was listening; now we know someone else is, too. This global review team fine-tunes the Amazon Echo's software by listening to clips of users asking Alexa questions or issuing commands, and then verifying whether Alexa responded appropriately. The team also annotates specific words the device struggles with when it's addressed in different accents. According to Amazon, users can opt out of the service, but they seem to be enrolled automatically.

To combat the robberies, Brazil's banks have invested in anti-theft technology, ranging from specialized ATMs to facial recognition cameras. When that fails or the costs become prohibitive, they have simply closed branches; as a result, some towns no longer have easy access to financial services in a country that already has a higher proportion of "unbanked" residents than either China or India.

An adversarial example is an input sample which is slightly modified to induce misclassification in an ML Dataset Number of Samples classifier. In this work, we investigate white-box and grey-box Training Set 57170 (28594 clean and 28576 malware) evasion attacks to an MLbased malware detector and conduct Validation Set 578 (280 clean and 298 malware) performance evaluations in a real-world setting. We compare Test Set 45028 (16154 clean and 28874 malware) the defense approaches in mitigating the attacks. We propose a framework for deploying grey-box and black-box attacks to malware detection systems.

Vikram Mahidhar reminds us all that AI is only as good as the humans supervising it and programming it. The biases and artefacts that come out of the processing are reflective of the biases programmed in at the beginning. A program trained to recognise totalled car bodies for insurance purposes, for example, will need close supervision of its decision-making outputs, for regulatory and consumer confidence and acceptance of the decision. There is a call and a growth in a new class of AI--one that is explainable, and that builds trust by providing evidence. Vikram also reminds us that a governance strategy is key to engendering trust in our organisation, processes and people.

In predictive process analytics, current and historical process data in event logs are used to predict future. E.g., to predict the next activity or how long a process will still require to complete. Recurrent neural networks (RNN) and its subclasses have been demonstrated to be well suited for creating prediction models. Thus far, event attributes have not been fully utilized in these models. The biggest challenge in exploiting them in prediction models is the potentially large amount of event attributes and attribute values. We present a novel clustering technique which allows for trade-offs between prediction accuracy and the time needed for model training and prediction. As an additional finding, we also found that this clustering method combined with having raw event attribute values provides even better prediction accuracy at the cost of additional time required for training and prediction. We also built a highly configurable test framework that can be used to efficiently evaluate different prediction approaches and parameterizations.