IMAGE: InSilico study reveals how E64 approaches, binds to, and inhibits falcipain-2 of Plasmodium falciparum that causes malaria in humans. Monday, November 12, 2018, Taipei, Taiwan, Republic of China - Insilico Taiwan, a Taipei-based subsidiary of Insilico Medicine, developing the end-to-end drug discovery pipeline utilizing the next generation artificial intelligence, announces the publication of a new research paper titled "In Silico Study Reveals How E64 Approaches, Binds to, and Inhibits Falcipain-2 of Plasmodium falciparum that Causes Malaria in Humans" in Scientific Reports - a scientific journal published by the Nature Publishing Group. Malaria is one of the world's oldest infectious diseases that still causes a lot of health problems in many tropical countries. Plasmodium falciparum, the most dangerous human malaria parasite, is believed to cause hundreds of millions of illnesses and about half a million deaths a year. Inhibitors of FP2 block haemoglobin destruction and parasite development, suggesting that FP2 inhibition is a promising target for antimalarial therapy.

Spectrum's internet has stopped working again, after a series of outages blamed on the ongoing California wildfires. The company has suffered repeated outages in the wake of the deadly fires, which it said had caused problems across Southern California. The latest problems have come from across the country: users from as far afield as Kentucky and Ohio have reported issues to Spectrum's Twitter account. As such, it isn't clear if the latest outages are related only to the wildfires. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.

Results of last week's U.S. midterm elections were mixed, leaving a chasm in the U.S. political landscape. The Republicans not only retained control of the Senate, but also gained more seats. The Democrats, meanwhile, took back the House of Representatives. But in terms of American foreign policy, a veteran New York Times columnist who was recently in Japan says that the election results are unlikely to affect President Donald Trump so much, and that he is likely to keep challenging Japan and China -- especially on trade issues. I don't think much will change regarding trade.

We now live in the world of AI and there's plenty of talk about what the future holds. With doubts about the future everywhere, one can predict that AI is soon going to be a key part of our lives. Considering the likely future impact of AI, there's a need to ensure that the right AI talent develops and rises to the top to lead this wave of change. According to several key leaders from Huawei, this can only be achieved by changing certain approaches. As a Huawei partner and a member of Huawei's Key Opinion Leader Program, I joined three other experts in conducting keynotes at Huawei Connect in Shanghai, all related to the question of how to develop talent in the AI era: Dr. Hao Lu, Chief Innovation Officer at Yitu, Huang Weiwei, Senior Management Consultant for Huawei, and Qian Wang, the Co-Founder of Mai Mai.

Anomaly detection using dimensionality reduction has been an essential technique for monitoring multidimensional data. Although deep learning-based methods have been well studied for their remarkable detection performance, their interpretability is still a problem. In this paper, we propose a novel algorithm for estimating the dimensions contributing to the detected anomalies by using variational autoencoders (VAEs). Our algorithm is based on an approximative probabilistic model that considers the existence of anomalies in the data, and by maximizing the log-likelihood, we estimate which dimensions contribute to determining data as an anomaly. The experiments results with benchmark datasets show that our algorithm extracts the contributing dimensions more accurately than baseline methods.

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn is associated with an increase in computational expense far surpassing mobile devices' capacity. What is worse, app service providers need to collect and utilize a large volume of users' data, which contain sensitive information, to build the sophisticated DNN models. Directly deploying these models on public mobile devices presents prohibitive privacy risk. To benefit from the on-device deep learning without the capacity and privacy concerns, we design a private model compression framework RONA. Following the knowledge distillation paradigm, we jointly use hint learning, distillation learning, and self learning to train a compact and fast neural network. The knowledge distilled from the cumbersome model is adaptively bounded and carefully perturbed to enforce differential privacy. We further propose an elegant query sample selection method to reduce the number of queries and control the privacy loss. A series of empirical evaluations as well as the implementation on an Android mobile device show that RONA can not only compress cumbersome models efficiently but also provide a strong privacy guarantee. For example, on SVHN, when a meaningful $(9.83,10^{-6})$-differential privacy is guaranteed, the compact model trained by RONA can obtain 20$\times$ compression ratio and 19$\times$ speed-up with merely 0.97% accuracy loss.

We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical algorithms, for optimizing univariate sub-problems with nice properties. From the other side, it also augments probabilities to receive desired results, by embedding advanced techniques in optimizations of realistic tasks. Integrating both numerical algorithms and advanced techniques together, TECU is proposed in a unified framework for solving a class of non-convex problems. Although the task embedded strategies bring inaccuracies in sub-problem optimizations, we provide a realizable criterion to control the errors, meanwhile, to ensure robust performances with rigid theoretical analyses. By respectively embedding ADMM and a residual-type CNN in our algorithm framework, the experimental results verify both efficiency and effectiveness of embedding task-oriented strategies in coordinate descent for solving practical problems.

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label information (such as class labels or pair/triplet constraints) to achieve satisfactory performance. However, the label information may be insufficient in real-world applications due to the high-labeling cost, and DML may fail in this case. Transfer metric learning (TML) is able to mitigate this issue for DML in the domain of interest (target domain) by leveraging knowledge/information from other related domains (source domains). Although achieved a certain level of development, TML has limited success in various aspects such as selective transfer, theoretical understanding, handling complex data, big data and extreme cases. In this survey, we present a systematic review of the TML literature. In particular, we group TML into different categories according to different settings and metric transfer strategies, such as direct metric approximation, subspace approximation, distance approximation, and distribution approximation. A summarization and insightful discussion of the various TML approaches and their applications will be presented. Finally, we indicate some challenges and provide possible future directions.

In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task at hand. In this work, we explore the possibility of learning a version of the agent's design that is better suited for its task, jointly with the policy. We propose a minor alteration to the OpenAI Gym framework, where we parameterize parts of an environment, and allow an agent to jointly learn to modify these environment parameters along with its policy. We demonstrate that an agent can learn a better structure of its body that is not only better suited for the task, but also facilitates policy learning. Joint learning of policy and structure may even uncover design principles that are useful for assisted-design applications. Videos of results at https://designrl.github.io/