KSG mutual information estimator, which is based on the distances of each sample to its k-th nearest neighbor, is widely used to estimate mutual information between two continuous random variables. Existing work has analyzed the convergence rate of this estimator for random variables whose densities are bounded away from zero in its support. In practice, however, KSG estimator also performs well for a much broader class of distributions, including not only those with bounded support and densities bounded away from zero, but also those with bounded support but densities approaching zero, and those with unbounded support. In this paper, we analyze the convergence rate of the error of KSG estimator for smooth distributions, whose support of density can be both bounded and unbounded. As KSG mutual information estimator can be viewed as an adaptive recombination of KL entropy estimators, in our analysis, we also provide convergence analysis of KL entropy estimator for a broad class of distributions.

We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analysis of consistency properties to the case of inconsistent surrogates. Our key technical contribution consists in a new lower bound on the calibration function for the quadratic surrogate, which is non-trivial (not always zero) for inconsistent cases. The new bound allows to quantify the level of inconsistency of the setting and shows how learning with inconsistent surrogates can have guarantees on sample complexity and optimization difficulty. We apply our theory to two concrete cases: multi-class classification with the tree-structured loss and ranking with the mean average precision loss. The results show the approximation-computation trade-offs caused by inconsistent surrogates and their potential benefits.

Discovery of atomistic systems with desirable properties is a major challenge in chemistry and material science. Here we introduce a novel, autoregressive, convolutional deep neural network architecture that generates molecular equilibrium structures by sequentially placing atoms in three-dimensional space. The model estimates the joint probability over molecular configurations with tractable conditional probabilities which only depend on distances between atoms and their nuclear charges. It combines concepts from state-of-the-art atomistic neural networks with auto-regressive generative models for images and speech. We demonstrate that the architecture is capable of generating molecules close to equilibrium for constitutional isomers of C$_7$O$_2$H$_{10}$.

Global demographic and economic changes have a critical impact on the total energy consumption, which is why demographic and economic parameters have to be taken into account when making predictions about the energy consumption. This research is based on the application of a multiple linear regression model and a neural network model, in particular multilayer perceptron, for predicting the energy consumption. Data from five Balkan countries has been considered in the analysis for the period 1995-2014. Gross domestic product, total number of population, and CO2 emission were taken as predictor variables, while the energy consumption was used as the dependent variable. The analyses showed that CO2 emissions have the highest impact on the energy consumption, followed by the gross domestic product, while the population number has the lowest impact. The results from both analyses are then used for making predictions on the same data, after which the obtained values were compared with the real values. It was observed that the multilayer perceptron model predicts better the energy consumption than the regression model.

In laser microsurgery, image-based control of the ablation laser can lead to higher accuracy and patient safety. However, camera-based image acquisition lacks the subcutaneous tissue perception. Optical coherence tomography (OCT) as high-resolution imaging modality yields transsectional images of tissue and can provide the missing depth information. Therefore, this paper deals with the tracking of distinctive subcutaneous structures on OCTs for automated control of ablation lasers in microsurgery. We present a deep learning based tracking scheme for concise representations of subsequent 3D OCT volumes. For each of the volume, a compact representation is created by calculating maximum intensity projections and projecting the depth value, were the maximum intensity voxel is found, onto an image plane. These depth images are then used for tracking by estimating the dense optical flow and depth changes with a self-supervisely trained convolutional neural network. Tracking performances are evaluated on a dataset of ex vivo human temporal bone with rigid ground truth transformations and on an in vivo sequence of human skin with non-rigid transformations. First quantitative evaluation reveals a mean endpoint error of 2.27voxel for scene flow estimation. Object tracking on 4D OCT data enables its use for sub-epithelial tracking of tissue structures for image-guidance in automated laser incision control for microsurgery.

We present a reinforcement learning approach for detecting objects within an image. Our approach performs a step-wise deformation of a bounding box with the goal of tightly framing the object. It uses a hierarchical tree-like representation of predefined region candidates, which the agent can zoom in on. This reduces the number of region candidates that must be evaluated so that the agent can afford to compute new feature maps before each step to enhance detection quality. We compare an approach that is based purely on zoom actions with one that is extended by a second refinement stage to fine-tune the bounding box after each zoom step. We also improve the fitting ability by allowing for different aspect ratios of the bounding box. Finally, we propose different reward functions to lead to a better guidance of the agent while following its search trajectories. Experiments indicate that each of these extensions leads to more correct detections. The best performing approach comprises a zoom stage and a refinement stage, uses aspect-ratio modifying actions and is trained using a combination of three different reward metrics.

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose a data-efficient training of a stacked convolutional and recurrent neural network. This neural network is trained in a multi instance learning setting for which we introduce a new loss function that leads to improved training compared to the usual approaches for weakly supervised learning. We successfully test our approach on two low-resource datasets that lack temporal labels.

Sentence embeddings have become an essential part of today's natural language processing (NLP) systems, especially together advanced deep learning methods. Although pre-trained sentence encoders are available in the general domain, none exists for biomedical texts to date. In this work, we introduce BioSentVec: the first open set of sentence embeddings trained with over 30 million documents from both scholarly articles in PubMed and clinical notes in the MIMIC-III Clinical Database. We evaluate BioSentVec embeddings in two sentence pair similarity tasks in different text genres. Our benchmarking results demonstrate that the BioSentVec embeddings can better capture sentence semantics compared to the other competitive alternatives and achieve state-of-the-art performance in both tasks. We expect BioSentVec to facilitate the research and development in biomedical text mining and to complement the existing resources in biomedical word embeddings.

Artificial intelligence has allowed the Art Institute of Chicago to track how long visitors stay in its galleries, leading it to offer more small exhibitions focusing on its permanent collection. And A.I. is aiding the conservation and attribution efforts of Robert Erdmann, senior scientist at the Rijksmuseum in Amsterdam. He is developing tools that allow visitors to his museum's website -- which contains over 300,000 digital photographs of objects in its collection -- to use artificial intelligence when they try to make comparisons among these objects, exploring, for example, all works -- beside the museum's famous Vermeer painting of a milkmaid -- of women preparing food. Another possible application of artificial intelligence, according to Elizabeth Merritt, director of the American Alliance of Museums' Center for the Future of Museums, could be the ability of visitors to interact with historical figures at history museums, through chatbots developed using the figures' published writings and archives, as well as oral histories. Robert Stein, executive vice president and chief program officer of the American Alliance of Museums, warned that museums must be aware of privacy issues as they use artificial intelligence, for example, protecting whatever personal information their visitors provide.

Artificial intelligence promises considerable economic benefits, even as it disrupts the world of work. Three priorities will help achieve good outcomes. This new article is by James Manyika and Jacques Bughin of the McKinsey Global Institute. I hope you find it useful. The time may have finally come for artificial intelligence (AI) after periods of hype followed by several "AI winters" over the past 60 years. AI now powers so many real-world applications, ranging from facial recognition to language translators and assistants like Siri and Alexa, that we barely notice it. Along with these consumer applications, companies across sectors are increasingly harnessing AI's power in their operations. Embracing AI promises considerable benefits for businesses and economies through its contributions to productivity growth and innovation.