Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging training sets. Previous work primarily focused on data augmentation for semi-supervised and supervised tasks. In this paper, we instead focus on unsupervised anomaly detection and propose a novel generative data augmentation framework optimized for this task. In particular, we propose to oversample infrequent normal samples - normal samples that occur with small probability, e.g., rare normal events. We show that these samples are responsible for false positives in anomaly detection. However, oversampling of infrequent normal samples is challenging for real-world high-dimensional data with multimodal distributions. To address this challenge, we propose to use a GAN variant known as the adversarial autoencoder (AAE) to transform the high-dimensional multimodal data distributions into low-dimensional unimodal latent distributions with well-defined tail probability. Then, we systematically oversample at the `edge' of the latent distributions to increase the density of infrequent normal samples. We show that our oversampling pipeline is a unified one: it is generally applicable to datasets with different complex data distributions. To the best of our knowledge, our method is the first data augmentation technique focused on improving performance in unsupervised anomaly detection. We validate our method by demonstrating consistent improvements across several real-world datasets.

This paper studies the problems of vehicle make & model classification. Some of the main challenges are reaching high classification accuracy and reducing the annotation time of the images. To address these problems, we have created a fine-grained database using online vehicle marketplaces of Turkey. A pipeline is proposed to combine an SSD (Single Shot Multibox Detector) model with a CNN (Convolutional Neural Network) model to train on the database. In the pipeline, we first detect the vehicles by following an algorithm which reduces the time for annotation. Then, we feed them into the CNN model. It is reached approximately 4% better classification accuracy result than using a conventional CNN model. Next, we propose to use the detected vehicles as ground truth bounding box (GTBB) of the images and feed them into an SSD model in another pipeline. At this stage, it is reached reasonable classification accuracy result without using perfectly shaped GTBB. Lastly, an application is implemented in a use case by using our proposed pipelines. It detects the unauthorized vehicles by comparing their license plate numbers and make & models. It is assumed that license plates are readable.

Individuals create and consume more diverse data about themselves today than any time in history. Sources of this data include wearable devices, images, social media, geospatial information and more. A tremendous opportunity rests within cross-modal data analysis that leverages existing domain knowledge methods to understand and guide human health. Especially in chronic diseases, current medical practice uses a combination of sparse hospital based biological metrics (blood tests, expensive imaging, etc.) to understand the evolving health status of an individual. Future health systems must integrate data created at the individual level to better understand health status perpetually, especially in a cybernetic framework. In this work we fuse multiple user created and open source data streams along with established biomedical domain knowledge to give two types of quantitative state estimates of cardiovascular health. First, we use wearable devices to calculate cardiorespiratory fitness (CRF), a known quantitative leading predictor of heart disease which is not routinely collected in clinical settings. Second, we estimate inherent genetic traits, living environmental risks, circadian rhythm, and biological metrics from a diverse dataset. Our experimental results on 24 subjects demonstrate how multi-modal data can provide personalized health insight. Understanding the dynamic nature of health status will pave the way for better health based recommendation engines, better clinical decision making and positive lifestyle changes.

Autonomous robots increasingly depend on third-party off-the-shelf components and complex machine-learning techniques. This trend makes it challenging to provide strong design-time certification of correct operation. To address this challenge, we present SOTER, a programming framework that integrates the core principles of runtime assurance to enable the use of uncertified controllers, while still providing safety guarantees. Runtime Assurance (RTA) is an approach used for safety-critical systems where design-time analysis is coupled with run-time techniques to switch between unverified advanced controllers and verified simple controllers. In this paper, we present a runtime assurance programming framework for modular design of provably-safe robotics software. \tool provides language primitives to declaratively construct a \rta module consisting of an advanced controller (untrusted), a safe controller (trusted), and the desired safety specification (S). If the RTA module is well formed then the framework provides a formal guarantee that it satisfies property S. The compiler generates code for monitoring system state and switching control between the advanced and safe controller in order to guarantee S. RTA allows complex systems to be constructed through the composition of RTA modules. To demonstrate the efficacy of our framework, we consider a real-world case-study of building a safe drone surveillance system. Our experiments both in simulation and on actual drones show that RTA-enabled RTA ensures safety of the system, including when untrusted third-party components have bugs or deviate from the desired behavior.

This paper addresses the problem of mapping natural language text to knowledge base entities. The mapping process is approached as a composition of a phrase or a sentence into a point in a multi-dimensional entity space obtained from a knowledge graph. The compositional model is an LSTM equipped with a dynamic disambiguation mechanism on the input word embeddings (a Multi-Sense LSTM), addressing polysemy issues. Further, the knowledge base space is prepared by collecting random walks from a graph enhanced with textual features, which act as a set of semantic bridges between text and knowledge base entities. The ideas of this work are demonstrated on large-scale text-to-entity mapping and entity classification tasks, with state of the art results.

Designing shared neural architecture plays an important role in multi-task learning. The challenge is that finding an optimal sharing scheme relies heavily on the expert knowledge and is not scalable to a large number of diverse tasks. Inspired by the promising work of neural architecture search (NAS), we apply reinforcement learning to automatically find possible shared architecture for multi-task learning. Specifically, we use a controller to select from a set of shareable modules and assemble a task-specific architecture, and repeat the same procedure for other tasks. The controller is trained with reinforcement learning to maximize the expected accuracies for all tasks. We conduct extensive experiments on two types of tasks, text classification and sequence labeling, which demonstrate the benefits of our approach.

Understanding the diffusion in social network is an important task. However, this task is challenging since (1) the network structure is usually hidden with only observations of events like "post" or "repost" associated with each node, and (2) the interactions between nodes encompass multiple distinct patterns which in turn affect the diffusion patterns. For instance, social interactions seldom develop on a single channel, and multiple relationships can bind pairs of people due to their various common interests. Most previous work considers only one of these two challenges which is apparently unrealistic. In this paper, we study the problem of \emph{inferring multiplex network} in social networks. We propose the Multiplex Diffusion Model (MDM) which incorporates the multivariate marked Hawkes process and topic model to infer the multiplex structure of social network. A MCMC based algorithm is developed to infer the latent multiplex structure and to estimate the node-related parameters. We evaluate our model based on both synthetic and real-world datasets. The results show that our model is more effective in terms of uncovering the multiplex network structure.

Above the Trend Line: your industry rumor central is a recurring feature of insideBIGDATA. In this column, we present a variety of short time-critical news items grouped by category such as M&A activity, people movements, funding news, financial results, industry alignments, customer wins, rumors and general scuttlebutt floating around the big data, data science and machine learning industries including behind-the-scenes anecdotes and curious buzz. Our intent is to provide you a one-stop source of late-breaking news to help you keep abreast of this fast-paced ecosystem. We're working hard on your behalf with our extensive vendor network to give you all the latest happenings. Be sure to Tweet Above the Trend Line articles using the hashtag: #abovethetrendline.

AIMinds brings some of the most well-known AI practitioners and researchers from India to exchange ideas, share knowledge and help budding professionals to make a career in this field. The first edition, held in Bengaluru was helmed by Monis Khan, CEO at Datoin, Hindol Basu, CEO at Actify Data Labs and Subramanian MS, head of Analytics at Bigbasket. The speakers addressed one of the biggest concerns -- Switching To A Career In Data science and Building Domain-specific Data Science Products. The recently concluded second edition on Demystifying Data Science was held at ISB, Hyderabad and was headed by Vikas Agarwal, senior principal data scientist at Oracle, Bhat Dittakavi, serial tech entrepreneur and Joy Mustafi, principal applied scientist at Microsoft AI & Research and Koteswararao Chilakala, technical lead at LVPEI Center for Innovation.

From apocalyptic prognostications to impassioned positions -- and everything in between -- it seems like everyone and their mother has developed an opinion on the role artificial intelligence (AI) will play in shaping society in the coming decades. The disparity between each of these notwithstanding, what's clear is that "narrow AI" is already starting to have an impact on everything from software development to education to insurance. Despite multiple dalliances with AI stretching all the way back to the 1970s, my industry, healthcare, has yet to embrace AI with the same vigor as many others. Fortunately, this is finally starting to change. Consulting firm Frost & Sullivan reports that the healthcare AI market is set to experience a compound annual growth rate of 40 percent through 2021, largely because AI has the potential to improve health care outcomes by 30 to 40 percent while simultaneously cutting the costs of treatment in half.