Learning color mixing is difficult for novice painters. In order to support novice painters in learning color mixing, we propose a prediction model for semitransparent pigment mixtures and use its prediction results to create a Smart Palette system. Such a system is constructed by first building a watercolor dataset with two types of color mixing data, indicated by transmittance and reflectance: incrementation of the same primary pigment and a mixture of two different pigments. Next, we apply the collected data to a deep neural network to train a model for predicting the results of semitransparent pigment mixtures. Finally, we constructed a Smart Palette that provides easily-followable instructions on mixing a target color with two primary pigments in real life: when users pick a pixel, an RGB color, from an image, the system returns its mixing recipe which indicates the two primary pigments being used and their quantities.

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship between the low-level features, and hence unable to capture the spatial hierarchies between low and high level features. The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer. The proposed SIFT Descriptor CNN therefore combines the feature extraction capabilities of CNN model and rotation invariance of SIFT descriptor. Experimental results on the MNIST and fashionMNIST datasets indicates reasonable improvements over conventional methods available in literature.

We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and remove outliers that lie away from this subspace. It is used together with an encoder and a decoder. The encoder maps the data into the latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a ``manifold" close to the original data. We illustrate algorithmic choices and performance for artificial data with corrupted manifold structure. We also demonstrate competitive precision and recall for image datasets.

Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.

Laboratory testing and medication prescription are two of the most important routines in daily clinical practice. Developing an artificial intelligence system that can automatically make lab test imputations and medication recommendations can save cost on potentially redundant lab tests and inform physicians in more effective prescription. We present an intelligent model that can automatically recommend the patients' medications based on their incomplete lab tests, and can even accurately estimate the lab values that have not been taken. We model the complex relations between multiple types of medical entities with their inherent features in a heterogeneous graph. Then we learn a distributed representation for each entity in the graph based on graph convolutional networks to make the representations integrate information from multiple types of entities. Since the entity representations incorporate multiple types of medical information, they can be used for multiple medical tasks. In our experiments, we construct a graph to associate patients, encounters, lab tests and medications, and conduct the two tasks: medication recommendation and lab test imputation. The experimental results demonstrate that our model can outperform the state-of-the-art models in both tasks.

Image representation is a fundamental task in computer vision. However, most of the existing approaches for image representation ignore the relations between images and consider each input image independently. Intuitively, relations between images can help to understand the images and maintain model consistency over related images. In this paper, we consider modeling the image-level relations to generate more informative image representations, and propose ImageGCN, an end-to-end graph convolutional network framework for multi-relational image modeling. We also apply ImageGCN to chest X-ray (CXR) images where rich relational information is available for disease identification. Unlike previous image representation models, ImageGCN learns the representation of an image using both its original pixel features and the features of related images. Besides learning informative representations for images, ImageGCN can also be used for object detection in a weakly supervised manner. The Experimental results on ChestX-ray14 dataset demonstrate that ImageGCN can outperform respective baselines in both disease identification and localization tasks and can achieve comparable and often better results than the state-of-the-art methods.

Automation is the key for businesses to increase their productivity and boost growth. Companies around the globe are increasingly switching to automation-related tools and software to optimize their workforce. Automation tools can complete repetitive and redundant tasks in real-time with great efficiency, allowing businesses to use their workforce towards more productive services. The advent of many intelligent technologies like machine learning (ML), artificial intelligence (AI), deep learning, and so on has played a significant role in the automation process. ML techniques use many powerful algorithms to help companies in getting insights into their business process and applications.

Medical researchers have unlocked an unsettling ability in artificial intelligence (AI): predicting a person's early death. Scientists recently trained an AI system to evaluate a decade of general health data submitted by more than half a million people in the United Kingdom. Then, they tasked the AI with predicting if individuals were at risk of dying prematurely -- in other words, sooner than the average life expectancy -- from chronic disease, they reported in a new study. The predictions of early death that were made by AI algorithms were "significantly more accurate" than predictions delivered by a model that did not use machine learning, lead study author Dr. Stephen Weng, an assistant professor of epidemiology and data science at the University of Nottingham (UN) in the U.K., said in a statement. To evaluate the likelihood of subjects' premature mortality, the researchers tested two types of AI: "deep learning," in which layered information-processing networks help a computer to learn from examples; and "random forest," a simpler type of AI that combines multiple, tree-like models to consider possible outcomes. Then, they compared the AI models' conclusions to results from a standard algorithm, known as the Cox model.

At each step, this book provides intuitive motivation, a summary of the most important equations relevant to the topic, and concludes with highly commented code for threaded computation on modern CPUs as well as massively parallel processing on computers with CUDA-capable video display cards. The first of three in a series on C and CUDA C deep learning and belief nets, Deep Belief Nets in C and CUDA C: Volume 1 shows you how the structure of these elegant models is much closer to that of human brains than traditional neural networks; they have a thought process that is capable of learning abstract concepts built from simpler primitives. As such, you'll see that a typical deep belief net can learn to recognize complex patterns by optimizing millions of parameters, yet this model can still be resistant to overfitting. All the routines and algorithms presented in the book are available in the code download, which also contains some libraries of related routines. Those who have at least a basic knowledge of neural networks and some prior programming experience, although some C and CUDA C is recommended.

We present RAPID (Real-time Automated Photometric IDentification), a novel time-series classification tool capable of automatically identifying transients from within a day of the initial alert, to the full lifetime of a light curve. Using a deep recurrent neural network with Gated Recurrent Units (GRUs), we present the first method specifically designed to provide early classifications of astronomical time-series data, typing 12 different transient classes. Our classifier can process light curves with any phase coverage, and it does not rely on deriving computationally expensive features from the data, making RAPID well-suited for processing the millions of alerts that ongoing and upcoming wide-field surveys such as the Zwicky Transient Facility (ZTF), and the Large Synoptic Survey Telescope (LSST) will produce. The classification accuracy improves over the lifetime of the transient as more photometric data becomes available, and across the 12 transient classes, we obtain an average area under the receiver operating characteristic curve of 0.95 and 0.98 at early and late epochs, respectively. We demonstrate RAPID's ability to effectively provide early classifications of transients from the ZTF data stream. We have made RAPID available as an open-source software package (https://astrorapid.readthedocs.io) for machine learning-based alert-brokers to use for the autonomous and quick classification of several thousand light curves within a few seconds.