With each passing year, our sector continues to demonstrate its evolving approach to fighting cyber threats, as cyber crime itself continues to evolve. As both business and government move forward with digital transformation initiatives to improve processes and efficiency, the overall security attack surface continues to expand with more potential points of access for criminals to exploit. However, our industry is tackling these challenges head-on, with numerous innovative solutions continuing to come to market. So, what have been the key trends of 2018 thus far? From attending trade shows, to speaking to customers, partners, analysts and the media, several examples have come to the forefront.

Future Tense is a partnership of Slate, New America, and Arizona State University that examines emerging technologies, public policy, and society. "If you look up the word stupid in the dictionary, there's a picture of you," went the sickest burn on the elementary school playground, back before the dictionary was dishing out sick burns of its own. Now Google basically is the dictionary, and real people's pictures come up when you perform a Google Image search for stupid. My recent results included a man with a condom over his head, a teenage boy in a hospital after attempting to complete the Duct Tape Challenge, and--I'm pleased to report--many pictures of Trump. It's a well-acknowledged problem that Google's algorithm determines what images are associated with your name--it's decided, for example, that a still of Rachel Withers, Commuter looking distraught the morning after Election Day 2016 is the second-most important image of me to share (though this is my own fault, for attaching it to an article about being distraught).

Seventy years ago was arguably the start of the modern computer age. A machine that took up an entire room at a laboratory in Manchester University ran its first programme at 11am on 21 June 1948. The prototype completed the task in 52 minutes, having run through 3.5 million calculations. The Manchester Baby, known formally as the Small-Scale Experimental Machine, was the world's first stored-program computer. It paved the way for the first commercially-available computers in a city known for centuries of science and innovation. Dr "Tommy" Gordon Thomas was 19 and in the final year of a physics degree at Manchester when he met Sir Freddie Williams, who designed The Baby with colleagues Tom Kilburn and Geoff Tootill.

Fast food, real estate, military operations, even home improvement -- many large industries will have to shift their strategies in the wake of driverless cars. It's all but a certainty that autonomous or driverless vehicles will be widely used in the United States at some point over the next two decades. Already, over two dozen major corporates including Google, Apple and Mercedes Benz are hard at work building their own self-driving vehicles. Tesla's Model S already includes an autopilot mode where the car drives itself on highways. Car ownership and driving habits are being completely reinvented. We'll explore the growing number of mobility technologies that are set to transform the current transportation ecosystem. Clearly tech and auto companies stand to gain, but many other industries could face serious upheavals unless they are able to adapt to the many changes self-driving cars will bring to the market. Below, we dive into 33 industries, from the obvious (professional driving & trucking) to the more surprising (fitness?), that will be shaken up by the advent of autonomous vehicles.

Many recent state-of-the-art recommender systems such as D-ATT, TransNet and DeepCoNN exploit reviews for representation learning. This paper proposes a new neural architecture for recommendation with reviews. Our model operates on a multi-hierarchical paradigm and is based on the intuition that not all reviews are created equal, i.e., only a select few are important. The importance, however, should be dynamically inferred depending on the current target. To this end, we propose a review-by-review pointer-based learning scheme that extracts important reviews, subsequently matching them in a word-by-word fashion. This enables not only the most informative reviews to be utilized for prediction but also a deeper word-level interaction. Our pointer-based method operates with a novel gumbel-softmax based pointer mechanism that enables the incorporation of discrete vectors within differentiable neural architectures. Our pointer mechanism is co-attentive in nature, learning pointers which are co-dependent on user-item relationships. Finally, we propose a multi-pointer learning scheme that learns to combine multiple views of interactions between user and item. Overall, we demonstrate the effectiveness of our proposed model via extensive experiments on \textbf{24} benchmark datasets from Amazon and Yelp. Empirical results show that our approach significantly outperforms existing state-of-the-art, with up to 19% and 71% relative improvement when compared to TransNet and DeepCoNN respectively. We study the behavior of our multi-pointer learning mechanism, shedding light on evidence aggregation patterns in review-based recommender systems.

We consider fractional hedonic games, a subclass of coalition formation games that can be succinctly modeled by means of a graph in which nodes represent agents and edge weights the degree of preference of the corresponding endpoints. The happiness or utility of an agent for being in a coalition is the average value she ascribes to its members. We adopt Nash stable outcomes as the target solution concept; that is we focus on states in which no agent can improve her utility by unilaterally changing her own group. We provide existence, efficiency and complexity results for games played on both general and specific graph topologies. As to the efficiency results, we mainly study the quality of the best Nash stable outcome and refer to the ratio between the social welfare of an optimal coalition structure and the one of such an equilibrium as to the price of stability. In this respect, we remark that a best Nash stable outcome has a natural meaning of stability, since it is the optimal solution among the ones which can be accepted by selfish agents. We provide upper and lower bounds on the price of stability for different topologies, both in case of weighted and unweighted edges. Beside the results for general graphs, we give refined bounds for various specific cases, such as triangle-free, bipartite graphs and tree graphs. For these families, we also show how to efficiently compute Nash stable outcomes with provable good social welfare.

There is no doubt that the artificial intelligence (AI) phenomenon will have a profound impact on businesses large and small this year; that part is easy to predict. What impact it will have, and whether this is a good or a bad thing, is harder to tell. Let's start with the basics of AI. "In our broad definition, AI is a collective term for computer systems that can sense their environment, think, learn, and take action in response to what they're sensing and their objectives. Forms of AI in use today include, among others, digital assistants, chatbots and machine learning. AI is already at work in industry (from sport and manufacturing to investing and healthcare). Here, we take a closer look at the AI trends and predictions for the coming year. There's always a tendency to think of AI as represented by emotionless robots. But humans are, well, humans, and we will continue to interact with AI in our very human way. Facial recognition software might have been developed with ...

In this article, we propose an approach that can make use of not only labeled EEG signals but also the unlabeled ones which is more accessible. We also suggest the use of data fusion to further improve the seizure prediction accuracy. Data fusion in our vision includes EEG signals, cardiogram signals, body temperature and time. We use the short-time Fourier transform on 28-s EEG windows as a pre-processing step. A generative adversarial network (GAN) is trained in an unsupervised manner where information of seizure onset is disregarded. The trained Discriminator of the GAN is then used as feature extractor. Features generated by the feature extractor are classified by two fully-connected layers (can be replaced by any classifier) for the labeled EEG signals. This semi-supervised seizure prediction method achieves area under the operating characteristic curve (AUC) of 77.68% and 75.47% for the CHBMIT scalp EEG dataset and the Freiburg Hospital intracranial EEG dataset, respectively. Unsupervised training without the need of labeling is important because not only it can be performed in real-time during EEG signal recording, but also it does not require feature engineering effort for each patient.

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this consistency using an auxiliary network that classifies the origin of the gradient tensor, and the main network serves as an adversary to the auxiliary network in addition to performing standard task-based training. We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable. For each of the three scenarios we show the potential of gradient adversarial training procedure. Specifically, gradient adversarial training increases the robustness of a network to adversarial attacks, is able to better distill the knowledge from a teacher network to a student network compared to soft targets, and boosts multi-task learning by aligning the gradient tensors derived from the task specific loss functions. Overall, our experiments demonstrate that gradient tensors contain latent information about whatever tasks are being trained, and can support diverse machine learning problems when intelligently guided through adversarialization using a auxiliary network.

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answering over a context. Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. MQAN shows improvements in transfer learning for machine translation and named entity recognition, domain adaptation for sentiment analysis and natural language inference, and zero-shot capabilities for text classification. We demonstrate that the MQAN's multi-pointer-generator decoder is key to this success and performance further improves with an anti-curriculum training strategy. Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting. We also release code for procuring and processing data, training and evaluating models, and reproducing all experiments for decaNLP.