After just three days using its new cutting-edge facial comparison biometric system, US customs intercepted an imposter posing as a French citizen trying to enter America. The 26-year-old man who was travelling from Sao Paulo, Brazil, last week became the first person to be caught out by the new technology, which is currently being tested at 14 international US airports. After the system alerted to a facial discrepancy, a search of the passenger revealed the man had concealed a Republic of Congo identification card in his shoe. He was deported without charge. US Customs and Border Protection hope the facial recognition software will detect terrorists and criminals before they can enter the US.

While neural networks have shown impressive performance on large datasets, applying these models to tasks where little data is available remains a challenging problem. In this paper we propose to use feature transfer in a zero-shot experimental setting on the task of semantic parsing. We first introduce a new method for learning the shared space between multiple domains based on the prediction of the domain label for each example. Our experiments support the superiority of this method in a zero-shot experimental setting in terms of accuracy metrics compared to state-of-the-art techniques. In the second part of this paper we study the impact of individual domains and examples on semantic parsing performance. We use influence functions to this aim and investigate the sensitivity of domain-label classification loss on each example. Our findings reveal that cross-domain adversarial attacks identify useful examples for training even from the domains the least similar to the target domain. Augmenting our training data with these influential examples further boosts our accuracy at both the token and the sequence level.

Abstract--We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new largescale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of state-of-the-art dehazing algorithms, and suggest promising future directions. A. Problem Description: Single Image Dehazing Images captured in outdoor scenes often suffer from poor visibility, reduced contrasts, fainted surfaces and color shift, due to the presence of haze. Caused by aerosols such as dust, mist, and fumes, the existence of haze adds complicated, nonlinear and data-dependent noise to the images, making the haze removal (a.k.a. Moreover, many computer vision algorithms can only work well with the scene radiance that is haze-free. However, a dependable vision system must reckon with the entire spectrum of degradations from unconstrained environments. Taking autonomous driving for example, hazy and foggy weather will obscure the vision of on-board cameras and create confusing reflections and glare, leaving state-of-the-art self-driving cars in struggle [1]. Boyi Li is with the Computer Science Department, Cornell University, USA.

A number of techniques have been proposed for aspect discovery using part of speech tagging (Hu and Liu, 2004), syntactic parsing (Lu et al., 2009), clustering (Mei et al., 2007; Titov and McDonald, 2008b), data mining (Ku et al., 2006), and information extraction (Popescu and Etzioni, 2005). Various lexicon and rule-based methods (Hu and Liu, 2004; Ku et al., 2006; Blair-Goldensohn et al., 2008) have been adopted for sentiment prediction together with a few learning approaches (Lu et al., 2009; Pappas and Popescu-Belis, 2017; Angelidis and Lapata, 2018). As for the summaries, a common format involves a list of aspects and the number of positive and negative opinions for each (Hu and Liu, 2004). While this format gives an overall idea of people's opinion, reading the actual text might be necessary to gain a better understanding of specific details. Textual summaries are created following mostly extractive methods (but see Ganesan et al. 2010 for an abstractive approach), and various formats ranging from lists of words (Popescu and Etzioni, 2005), to phrases (Lu et al., 2009), and sentences (Mei et al., 2007; Blair-Goldensohn et al., 2008; Lerman et al., 2009; Wang and Ling, 2016). In this paper, we present a neural framework for opinion extraction from product reviews. We follow the standard architecture for aspect-based summarization, while taking advantage of the success of neural network models in learning continuous features without recourse to preprocessing tools or linguistic annotations.

The recent CIO Summit saw executives across Australia coming together to discuss cutting-edge technology trends and management strategies. The event featured a heavyweight line-up of speakers and moderators, carefully selected to encourage discussion and challenge the status quo. IT Brief spoke to Huawei Australia chief technology officer David Soldani about his key takeaways from the event. That the world is changing fast, profoundly impacting every person, home, and organisation. For example, by 2025, 80% of people will have access to mobile broadband and the mobile traffic per day will rise from 30MB to 4GB per day; 75% of households will enjoy broadband services with 20 billion devices connected, with 12% of those being smart robots.

The 51-year-old artificial intelligence and robotics scientist is responsible for co-developing Google Street View, pioneering self-driving cars, founding Google X – the internet giant's secretive research lab – and revolutionising education by kickstarting massive open online courses (Moocs). His most recent project is developing flying cars. You launched your flying car company, Kitty Hawk, in 2015 backed by Google co-founder Larry Page and you have two projects in development – a personal aircraft called Flyer and an autonomous air taxi called Cora. Why do we need flying cars? The ground is getting more and more congested – we are all stuck in traffic all the time.

Existing fuzzy neural networks (FNNs) are mostly developed under a shallow network configuration having lower generalization power than those of deep structures. This paper proposes a novel self-organizing deep fuzzy neural network, namely deep evolving fuzzy neural networks (DEVFNN). Fuzzy rules can be automatically extracted from data streams or removed if they play little role during their lifespan. The structure of the network can be deepened on demand by stacking additional layers using a drift detection method which not only detects the covariate drift, variations of input space, but also accurately identifies the real drift, dynamic changes of both feature space and target space. DEVFNN is developed under the stacked generalization principle via the feature augmentation concept where a recently developed algorithm, namely Generic Classifier (gClass), drives the hidden layer. It is equipped by an automatic feature selection method which controls activation and deactivation of input attributes to induce varying subsets of input features. A deep network simplification procedure is put forward using the concept of hidden layer merging to prevent uncontrollable growth of input space dimension due to the nature of feature augmentation approach in building a deep network structure. DEVFNN works in the sample-wise fashion and is compatible for data stream applications. The efficacy of DEVFNN has been thoroughly evaluated using six datasets with non-stationary properties under the prequential test-then-train protocol. It has been compared with four state-of the art data stream methods and its shallow counterpart where DEVFNN demonstrates improvement of classification accuracy.

Algorithms increasingly govern our social world, transforming data into scores or rankings that decide who gets credit, jobs, dates, policing, and much more. The field of "algorithmic accountability" has arisen to highlight the problems with such methods of classifying people, and it has great promise: Cutting-edge work in critical algorithm studies applies social theory to current events; law and policy experts seem to publish new articles daily on how artificial intelligence shapes our lives, and a growing community of researchers has developed a field known as "Fairness, Accuracy, and Transparency in Machine Learning." The social scientists, attorneys, and computer scientists promoting algorithmic accountability aspire to advance knowledge and promote justice. But what should such "accountability" more specifically consist of? At a two-day, interdisciplinary roundtable on AI ethics I recently attended, such questions featured prominently, and humanists, policy experts, and lawyers engaged in a free-wheeling discussion about topics ranging from robot arms races to computationally planned economies.

South Korean tech Major LG Electronics has announced that Google Assistant is coming to its 2018 line-up of artificial intelligence (AI)-enabled ThinQ TVs in seven new countries. The company's ThinQ TVs came with integrated Google's digital assistant when they were introduced in the US and added support for Amazon's virtual assistant Alexa's commands soon after. "Google Assistant will be available in Canada, Australia and the UK, with support coming to South Korea, Spain, France and Germany by the end of the year," The Verge reported late on Friday. "The built-in ThinQ AI, which runs on LG's own'WebOS' can be used for TV-specific commands, such as'search for the soundtrack of this movie', while Google Assistant and Alexa can be used as a smart home hub," it said. The company was also planning on bringing Amazon Alexa support to Australia and Canada in the future.

According to the World Economic Forum and Deloitte report, released today, AI will dramatically upend the traditional dynamics of the financial services system, and this is good news for customers. "Banks today may have customers who aren't willing to change banks because of the high costs associated and the effort involved with shifting mortgages," Deloitte Australia digital partner Joel Lipman said. "But the future will see these costs removed as AI developments, such as personal banking assistants, are able to identify the best deal for customers and move them without the current high dependency on humans." He said this will be the "new battlefield for customer loyalty" as past barriers to switching, like cost, speed and access are eroded. At the same time, consumers can expect tailored banking solutions, which will also shift the existing dynamics. "As past methods of differentiation erode, AI presents an opportunity for institutions to escape a'race to the bottom' in price competition by introducing new ways to distinguish themselves to customers," the report said.