Minimizing a convex, quadratic objective is a fundamental problem in machine learning and optimization. In this work, we study prove information-theoretic, gradient query complexity lower bounds for minimizing convex quadratic functions, which, unlike prior works, apply even for randomized algorithms. Specifically, we construct a distribution over quadratic functions that witnesses lower bounds which match those known for deterministic algorithms, up to multiplicative constants. The distribution which witnesses our lower bound is in fact quite benign: it is both closed form, and derived from classical ensembles in random matrix theory. We believe that our construction constitutes a plausible "average case" setting, and thus provides compelling evidence that the worst case and average case complexity of convex-quadratic optimization are essentially identical.

Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks. This requires considerable efforts, from the scientific community, to find new algorithms that solve computer vision problems, such as object recognition. The diffusion of RGB-D cameras directed the study towards the research of new architectures able to exploit the RGB and Depth information. The project that is developed in this thesis concerns the realization of a new end-to-end architecture for the recognition of RGB-D objects called RCFusion. Our method generates compact and highly discriminative multi-modal features by combining complementary RGB and depth information representing different levels of abstraction. We evaluate our method on standard object recognition datasets, RGB-D Object Dataset and JHUIT-50. The experiments performed show that our method outperforms the existing approaches and establishes new state-of-the-art results for both datasets.

Approximate Bayesian computation (ABC) is a method for Bayesian inference when the likelihood is unavailable but simulating from the model is possible. However, many ABC algorithms require a large number of simulations, which can be costly. To reduce the computational cost, Bayesian optimisation (BO) and surrogate models such as Gaussian processes have been proposed. Bayesian optimisation enables one to intelligently decide where to evaluate the model next but common BO strategies are not designed for the goal of estimating the posterior distribution. Our paper addresses this gap in the literature. We propose to compute the uncertainty in the ABC posterior density, which is due to a lack of simulations to estimate this quantity accurately, and define a loss function that measures this uncertainty. We then propose to select the next evaluation location to minimise the expected loss. Experiments show that the proposed method often produces the most accurate approximations as compared to common BO strategies.

In ontology-based data access (OBDA), ontologies have been successfully employed for querying possibly unstructured and incomplete data. In this paper, we advocate using ontologies not only to formulate queries and compute their answers, but also for modifying queries by relaxing or restraining them, so that they can retrieve either more or less answers over a given dataset. Towards this goal, we first illustrate that some domain knowledge that could be naturally leveraged in OBDA can be expressed using complex role inclusions (CRI). Queries over ontologies with CRI are not first-order (FO) rewritable in general. We propose an extension of DL-Lite with CRI, and show that conjunctive queries over ontologies in this extension are FO rewritable. Our main contribution is a set of rules to relax and restrain conjunctive queries (CQs). Firstly, we define rules that use the ontology to produce CQs that are relaxations/restrictions over any dataset. Secondly, we introduce a set of data-driven rules, that leverage patterns in the current dataset, to obtain more fine-grained relaxations and restrictions.

Natural language processing is a type of artificial intelligence in which computational and mathematical methods are used to analyze the human language. NPL's goal for end users is to facilitate interactions with computers using conversational language. Subtopics in this genre include natural language understanding, which is about understanding the inputs created by humans, and natural language generation, which focuses on generating natural language narratives. The most popular approaches to NLP use machine learning, said Adrian Bowles, vice president of Research and lead analyst at Aragon Research. "At the most advanced levels in the research labs today, we see applications or systems like Google Duplex, which can act as an agent to perform tasks like scheduling haircuts over the phone by engaging with humans, or IBM's Debater, which can detect patterns of logical arguments in free form text and construct a coherent and novel narrative position statement."

The intelligent network market report aims at estimating the market size and growth potential of the market across segments: application, end-user, enterprise size, and region. Northbrook, IL -- (SBWIRE) -- 07/30/2018 -- The information cognition segment is expected to grow faster during the forecast period. Among applications, information cognition is expected to have a larger market share during the forecast period, as there is an increasing need for information cognition on data accumulation of networking operations which include network characteristics, trace route, traffic matrix, and other such data functionalities. The telecom service providers segment is estimated to have the largest market size in 2018. Among end-users, the cloud service providers segment is expected to grow at the fastest rate during the forecast period.

Health insurance is a critical component of the healthcare industry with private health insurance expenditures alone estimated at $1.1 billion in 2016, according to the latest data available from the Centers for Medicare and Medicaid Services. This figure represents 34 percent of the 2016 National Health Expenditure at $3.3 trillion. In this article, we will look at four AI applications that are tackling problems of underutilization and fraud in the insurance industry. Some applications below claim that they are using artificial intelligence to help improve health insurance cost efficiency, while reducing waste of money on underutilized or preventable care. Other applications claim to detect fraudulent claims.

Programmer Animesh Karnewar wanted to know how characters described in books would appear in reality, so he turned to artificial intelligence to see if it could properly render these fictional people. Called T2F, the research project uses a generative adversarial network (GAN) to encode text and synthesize facial images. Simply put, a GAN consists of two neural networks that argue with each other to produce the best results. For example, the job of network No. 1 is to fool network No. 2 into believing a rendered image is a real photograph while network No. 2 sets out to prove the alleged photo is just a rendered image. This back-and-forth process fine-tunes the rendering process until network No. 2 is eventually fooled.

Automated facial recognition systems from Japanese biz NEC will be used on staffers and athletes at the Tokyo 2020 Olympics. The technology – which is not without its detractors in the UK – was demonstrated at a media event in the city today. It will require athletes, staff, volunteers and the press to submit their photographs before the games start. These will then be linked up to IC chips in their passes and combined with scanners on entry to allow them access to more than 40 facilities. Tsuyoshi Iwashita, head of security for the games, said the aim was to reduce pressure on entry points and shorten queueing time for this group of people.

If you suffer with a short temper – you're probably not as smart as you think you are, a new study has found. Angry people are more likely to overestimate their intelligence levels than those with a calmer disposition, scientists have found. That's because being angry is linked with high levels of narcissism, as well as a greater belief in their abilities and competence. Those with a short fuse were also more likely to have problems maintaining a stable relationship, according to the latest findings. This is because individuals with high levels of narcissism struggle to establish bonds with others as they are always trying to dominate them.