The idea of Innovation Search was proposed as a data clustering method in which the directions of innovation were utilized to compute the adjacency matrix and it was shown that Innovation Pursuit can notably outperform the self representation based subspace clustering methods. In this paper, we present a new discovery that the directions of innovation can be used to design a provable and strong robust (to outlier) PCA method. The proposed approach, dubbed iSearch, uses the direction search optimization problem to compute an optimal direction corresponding to each data point. iSearch utilizes the directions of innovation to measure the innovation of the data points and it identifies the outliers as the most innovative data points. Analytical performance guarantees are derived for the proposed robust PCA method under different models for the distribution of the outliers including randomly distributed outliers, clustered outliers, and linearly dependent outliers. In addition, we study the problem of outlier detection in a union of subspaces and it is shown that iSearch provably recovers the span of the inliers when the inliers lie in a union of subspaces. Moreover, we present theoretical studies which show that the proposed measure of innovation remains stable in the presence of noise and the performance of iSearch is robust to noisy data. In the challenging scenarios in which the outliers are close to each other or they are close to the span of the inliers, iSearch is shown to remarkably outperform most of the existing methods. The presented method shows that the directions of innovation are useful representation of the data which can be used to perform both data clustering and outlier detection.

--While Deep Neural Networks (DNNs) trained for image and video super-resolution regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their tendency to generate strong artifacts in their solution. This may occur when the low-resolution image formation model does not match that seen during training. Artifacts also regularly arise when training Generative Adversarial Networks for inverse imaging problems. In this paper, we propose an efficient, fully self-supervised approach to remove the observed artifacts. More specifically, at test time, given an image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data consistency loss. We apply our method to image and video super-resolution neural networks and show that our proposed framework consistently enhances the solution originally provided by the neural network. In the past decade, the application of Deep Neural Networks (DNNs) to solving inverse imaging problems has gained considerable popularity [ 2 ]. The observed image y is assumed to come from a known image formation model with degradation operator A, which we formulate here as y Ax ǫ, where ǫ denotes the noise. The parameters ψ are learned through a lengthy training stage which requires the use of a large dataset of input-output (y, x) pairs. The training data is commonly generated by applying the degradation operator A to the clean images to obtain the corresponding degraded images used for training. With this straightforward framework combined with the fast-growing nature of Deep Learning, new state-of-the-art results for image restoration tasks are regularly achieved. Preliminary results of this work were presented at the 2019 IEEE International Conference on Image Processing (ICIP) [ 1 ].

In recent years, numerous benchmarks for commonsense reasoning have been presented which cover different areas: the Choice of Plausible Alternatives Challenge (COP A) [17] requires causal reasoning in everyday situations, the Winograd Schema Challenge [8] addresses difficult cases of pronoun disambiguation, the TriangleCOP A Challenge [9] focuses on human relationships and emotions, and the Story Cloze Test with the ROCStories Corpora [11] focuses on the ability to determine a plausible ending for a given short story, to name just a few. In our system, we focus on the COP A challenge where each problem consists of a problem description (the premise), a question, and two answer candidates (called alternatives). See Figure 1 for an example. Most approaches tackling these problems are based on machine learning or exploit statistical properties of the natural language input (see e.g.

We consider intuitionistic variants of linear temporal logic with `next', `until' and `release' based on expanding posets: partial orders equipped with an order-preserving transition function. This class of structures gives rise to a logic which we denote $\iltl$, and by imposing additional constraints we obtain the logics $\itlb$ of persistent posets and $\itlht$ of here-and-there temporal logic, both of which have been considered in the literature. We prove that $\iltl$ has the effective finite model property and hence is decidable, while $\itlb$ does not have the finite model property. We also introduce notions of bounded bisimulations for these logics and use them to show that the `until' and `release' operators are not definable in terms of each other, even over the class of persistent posets.

X-rays are a well-established tool to help analyze and restore valuable paintings because the rays' higher frequency means they pass right through paintings without harming them. X-ray imaging can reveal anything that has been painted over a canvas or where the artist may have altered his (or her) original vision. But the technique has its limitations, and that's where machine learning can prove useful. Two papers this fall illustrated the use of AI to solve specific problems in art analysis and conservation: one to reconstruct an underpainting in greater detail, and the other to make it easier to image two-sided painted panels. Picasso's The Old Guitarist is one of the best-known works from the artist's so-called "Blue Period."

Increased market for cloud computing 3.5.1.2. Growth associated with artificial intelligence and cognitive computing 3.5.2.

Increased market for cloud computing 3.5.1.2. Growth associated with artificial intelligence and cognitive computing 3.5.2.

Learning knowledge representation is an increasingly important technology applicable in many domain-specific machine learning problems. We discuss the effectiveness of traditional Link Prediction or Knowledge Graph Completion evaluation protocol when embedding knowledge representation for categorised multi-relational data in the clinical domain. Link prediction uses to split the data into training and evaluation subsets, leading to loss of information along training and harming the knowledge representation model accuracy. We propose a Clustering Evaluation Protocol as a replacement alternative to the traditionally used evaluation tasks. We used embedding models trained by a knowledge embedding approach which has been evaluated with clinical datasets. Experimental results with Pearson and Spearman correlations show strong evidence that the novel proposed evaluation protocol is pottentially able to replace link prediction.

Recommender Systems (RS) have became a popular research topic and, since 2016, Deep Learning methods and techniques have been increasingly explored in this area. News RS are aimed to personalize users experiences and help them discover relevant articles from a large and dynamic search space. The main contribution of this research was named CHAMELEON, a Deep Learning meta-architecture designed to tackle the specific challenges of news recommendation. It consists of a modular reference architecture which can be instantiated using different neural building blocks. As information about users' past interactions is scarce in the news domain, the user context can be leveraged to deal with the user cold-start problem. Articles' content is also important to tackle the item cold-start problem. Additionally, the temporal decay of items (articles) relevance is very accelerated in the news domain. Furthermore, external breaking events may temporally attract global readership attention, a phenomenon generally known as concept drift in machine learning. All those characteristics are explicitly modeled on this research by a contextual hybrid session-based recommendation approach using Recurrent Neural Networks. The task addressed by this research is session-based news recommendation, i.e., next-click prediction using only information available in the current user session. A method is proposed for a realistic temporal offline evaluation of such task, replaying the stream of user clicks and fresh articles being continuously published in a news portal. Experiments performed with two large datasets have shown the effectiveness of the CHAMELEON for news recommendation on many quality factors such as accuracy, item coverage, novelty, and reduced item cold-start problem, when compared to other traditional and state-of-the-art session-based recommendation algorithms.

The Royal Academy of Engineering's Africa prize, now in its sixth year, is the continent's biggest award for engineering innovation. Sixteen African inventors from six countries – including, for the first time, Malawi – have been shortlisted to receive funding, training and mentoring for projects intended to revolutionise sectors ranging from agriculture and banking to women's health. The winner will be awarded £25,000 and the three runners-up will receive £10,000 each. This year's inventions include facial recognition software to prevent financial fraud, a low-cost digital microscope to speed up cervical cancer diagnosis, and two separate innovations made from water hyacinth plants. Four inventors spoke to the Guardian about their innovations and their plans to change Africa for the better.