Oral Disintegrating Tablets (ODTs) is a novel dosage form that can be dissolved on the tongue within 3min or less especially for geriatric and pediatric patients. Current ODT formulation studies usually rely on the personal experience of pharmaceutical experts and trial-and-error in the laboratory, which is inefficient and time-consuming. The aim of current research was to establish the prediction model of ODT formulations with direct compression process by Artificial Neural Network (ANN) and Deep Neural Network (DNN) techniques. 145 formulation data were extracted from Web of Science. All data sets were divided into three parts: training set (105 data), validation set (20) and testing set (20). ANN and DNN were compared for the prediction of the disintegrating time. The accuracy of the ANN model has reached 85.60%, 80.00% and 75.00% on the training set, validation set and testing set respectively, whereas that of the DNN model was 85.60%, 85.00% and 80.00%, respectively. Compared with the ANN, DNN showed the better prediction for ODT formulations. It is the first time that deep neural network with the improved dataset selection algorithm is applied to formulation prediction on small data. The proposed predictive approach could evaluate the critical parameters about quality control of formulation, and guide research and process development. The implementation of this prediction model could effectively reduce drug product development timeline and material usage, and proactively facilitate the development of a robust drug product.

The availability of a large amount of electronic health records (EHR) provides huge opportunities to improve health care service by mining these data. One important application is clinical endpoint prediction, which aims to predict whether a disease, a symptom or an abnormal lab test will happen in the future according to patients' history records. This paper develops deep learning techniques for clinical endpoint prediction, which are effective in many practical applications. However, the problem is very challenging since patients' history records contain multiple heterogeneous temporal events such as lab tests, diagnosis, and drug administrations. The visiting patterns of different types of events vary significantly, and there exist complex nonlinear relationships between different events. In this paper, we propose a novel model for learning the joint representation of heterogeneous temporal events. The model adds a new gate to control the visiting rates of different events which effectively models the irregular patterns of different events and their nonlinear correlations. Experiment results with real-world clinical data on the tasks of predicting death and abnormal lab tests prove the effectiveness of our proposed approach over competitive baselines.

This is the second installment in a three-part series exploring the impact of artificial intelligence (NYSE:AI) on investment management. I want to thank the speakers at the AI and the Future of Financial Services Forum, hosted by CFA Institute and CFA Society Beijing, for inspiring this series. The first installment offered a primer on the AI technologies that are relevant to investment professionals. Artificial intelligence (AI) is coming to the investment world. With the help of deep learning techniques, AI researchers have made significant strides in natural language processing (NLP), speech recognition, and image recognition.

Is nothing safe from the reach of the machines? After replacing humans at repetitive tasks, beating them at games of skill, artificial intelligence is now making inroads into the arguably the last frontier: the creative arts. Ping An Technology, a subsidiary of China's second-largest life insurance company, has developed an award-winning computer algorithm that can generate original melodies after "studying" hundreds of pieces of piano music. But the company has no intention of stopping there. It is working towards using AI to create virtual singers and write original pop music based on individual tastes with a longer term goal of composing a symphony to potentially rival Beethoven. "Be it a Chinese version of break-up songs similar to Taylor Swift's style or a Shanghai accented voice that raps like Justin Bieber, with the upgrade of the AI music system we will be able to create whatever music you like as long as we know the genre and the type of singers you adore," said Xiao Jing, chief scientist of Ping An Technology.

Apple will reveal the future of the iPhone and its other products at WWDC in June. The company has announced its annual software conference will take place between 4 June and 9 June. The big event will happen on the first of those days: a major keynote presentation in which Apple executives reveal the latest versions of the software for the iPhone, iPad, Macs, Apple TV and other products. Apple event suggested that updates could come to the latest of its products: the HomePod. Usually, every single one of Apple's products gets an update – though very few new products are usually revealed, the event serves as the launch for updates to its entire suite of software.

A common problem for any scaling business is bringing on the right help at the right time. Small-business owners often find that the people they can afford don't have the skills or experience to do the job well, and the people they want cost too much relative to the business's current cash flow. Most of the work is labor intensive, repetitive, boring and must be done correctly. As luck would have it, that's exactly the kind of tasks we build computers to do. In the past 15 or so years, outsourcing to international assistants and part-time workers has been the go-to solution for entrepreneurs looking to grow on a budget.

A global race is on to develop artificial intelligence -- and it matters enormously who wins. Another reminder of that fact came at the beginning of February when China started equipping its police officers with facial-recognition eyewear. Cameras mounted on sunglasses and linked to a police database will help officers track wanted criminals -- or, presumably, anyone else the Chinese government takes an interest in. Throw in research showing that computers can be trained to recognize traits like homosexuality, and the dystopian narratives start to write themselves. We're just scratching the surface of what we can do with AI.

Check out the AI Conference in Beijing, April 10-13, 2018. Hurry--early price ends March 9. Having traveled to China several times over the last few years, I can attest to the strong interest in applications of AI among technologists, business leaders, and policy makers. China is adopting AI tools and technologies at a rapid pace, and since current AI systems rely on large data sets, startups are able to start using AI tools much earlier (a startup in China can quickly have many millions of users). People in the West are curious about the progress of AI research and business models in China. On the flip side, having organized a couple of large conferences in Beijing, I also know that people in China want to hear from AI experts outside their country.

Binance, the China-based cryptocurrency exchange that was targeted by a failed heist last week, has placed a $250,000 (£179,000) bounty on the heads of the cyber-criminals responsible. The failed raid saw the would-be thieves - still unidentified - using a phishing scam to acquire coin traders' login details before generating API keys to access their accounts, buying large quantities of viacoin and then attempting to exchange that suddenly-inflated currency for bitcoin. It was at this point that the site's moderators noticed the suspicious activity and stepped in to block the transactions, preventing any money from being stolen. "To ensure a safe crypto community, we can't simply play defence," Binance said in a statement. "We need to actively prevent any instances of hacking before they occur, as well as follow through after-the-fact.

World governments have an insatiable need to make incremental improvements in the services they deliver while at the same time tackling the longer-term public sector challenges that limit their socioeconomic potential. As leading nations have discovered, the right use of digital technology is the pathway to achieving both objectives. Successful nations have technology strategies that are both aggressively practical and profoundly aspirational. A breakthrough global public-private partnership recently collaborated to identify the top 10 government technology (govtech) initiatives worldwide that will contribute the most to sustainable improvements in 192 countries' economies and societies. MIT Technology Review Insights and the United Arab Emirates-based World Government Summit (WGS), a non-government organization promoting future-oriented public-private dialogue, worked together to select the most interesting govtech implementations from among the world's more innovative initiatives.