Deep generative models such as generative adversarial networks, variational autoencoders, and autoregressive models are rapidly growing in popularity for the discovery of new molecules and materials. In this work, we introduce MOlecular SEtS (MOSES), a benchmarking platform to support research on machine learning for drug discovery. MOSES implements several popular molecular generation models and includes a set of metrics that evaluate the diversity and quality of generated molecules. MOSES is meant to standardize the research on the molecular generation and facilitate the sharing and comparison of new models. Additionally, we provide a large-scale comparison of existing state of the art models and elaborate on current challenges for generative models that might prove fertile ground for new research. Our platform and source code are freely available at https://github.com/molecularsets/

Nov 28, 2018 Ginny Engholm Danny Iny, on How to Future-Proof Your Job Digital disruption is transforming the world of work. The skills that workers will need in the long term are changing at a rapid pace, and this is causing employees -- and employers -- a lot of anxiety. Workers fear being replaced by tech for good reason -- a 2017 report from PricewaterhouseCoopers estimated that 38 percent of U.S. jobs are at risk of being replaced by automation by the early 2030s. Some industries, such as transportation, wholesale, manufacturing and retail, are particularly vulnerable to automation. But no industry is safe.

Replanting trees after a wildfire or logging operation is an extremely labor intensive and expensive task. Carrying a bag of seedlings and using a dibble bar or shovel across steep debris-covered terrain can wear out a human. A new company, DroneSeed, has a solution. They are designing a system around a swarm of drones that can plant tree seeds in places where they have a decent chance of survival. First they survey the area with a drone using lidar and a multispectral camera to map the terrain and the vegetation.

Manifold embedding algorithms map high dimensional data, down to coordinates in a much lower dimensional space. One of the aims of the dimension reduction is to find the {\em intrinsic coordinates} that describe the data manifold. However, the coordinates returned by the embedding algorithm are abstract coordinates. Finding their physical, domain related meaning is not formalized and left to the domain experts. This paper studies the problem of recovering the domain-specific meaning of the new low dimensional representation in a semi-automatic, principled fashion. We propose a method to explain embedding coordinates on a manifold as {\em non-linear} compositions of functions from a user-defined dictionary. We show that this problem can be set up as a sparse {\em linear Group Lasso} recovery problem, find sufficient recovery conditions, and demonstrate its effectiveness on data.

We present a generative approach to classify scarcely observed longitudinal patient trajectories. The available time series are represented as tensors and factorized using generative deep recurrent neural networks. The learned factors represent the patient data in a compact way and can then be used in a downstream classification task. For more robustness and accuracy in the predictions, we used an ensemble of those deep generative models to mimic Bayesian posterior sampling. We illustrate the performance of our architecture on an intensive-care case study of in-hospital mortality prediction with 96 longitudinal measurement types measured across the first 48-hour from admission. Our combination of generative and ensemble strategies achieves an AUC of over 0.85, and outperforms the SAPS-II mortality score and GRU baselines.

Range Rover has unveiled its latest'green' compact luxury 4X4 with'X-Ray vision' that enable drivers to'see' through the bonnet to view what lies on beneath on the road below and'eyes in the back of its head' to show what's coming up behind. The new second-generation British-built Evoque off-roader is built with electrification and hybrid power in mind, and has a non-leather cloth option designed for vegetarians and vegans and made from recycled plastic bottles. Significantly, it features unique'ground view' technology that makes its bonnet'invisible' to the driver so he or she has a view of any rough or extreme terrain - or high city centre kerbs - that are lurking underneath or just ahead, but normally out of sight. The firm said its ClearSight Ground View technology marks'a world first' for the compact luxury 4X4 which is powered by a range of mild-hybrid petrol and diesel engines, with a plug in hybrid to follow next year and the potential for a fully electric version. Range Rover has unveiled its latest'green' compact luxury 4X4 with'X-Ray vision' that enable drivers to'see' through the bonnet to view what lies on beneath on the road below Significantly, it features unique'ground view' technology that makes its bonnet'invisible' to the driver so he or she has a view of any rough or extreme terrain - or high city centre kerbs - that are lurking underneath or just ahead, but normally out of sight The new all-seeing Evoque was unveiled at a star-studded international launch at the Old Truman Brewery in East London's trendy Brick Lane where fashion and Vogue cover model Adwoa Aboah was to appear wearing a dress made out of the very same Kvadrat material made from recycled plastic bottles.

Keyword spotting--or wakeword detection--is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword. In this work, we present DONUT, a CTC-based algorithm for online query-by-example keyword spotting that enables custom wakeword detection. The algorithm works by recording a small number of training examples from the user, generating a set of label sequence hypotheses from these training examples, and detecting the wakeword by aggregating the scores of all the hypotheses given a new audio recording. Our method combines the generalization and interpretability of CTC-based keyword spotting with the user-adaptation and convenience of a conventional query-by-example system. DONUT has low computational requirements and is well-suited for both learning and inference on embedded systems without requiring private user data to be uploaded to the cloud.

How to effectively address the domain adaptation problem is a challenging task for person re-identification (reID). In this work, we make the first endeavour to tackle this issue according to one shot learning. Given an annotated source training set and a target training set that only one instance for each category is annotated, we aim to achieve competitive re-ID performance on the testing set of the target domain. To this end, we introduce a similarity-guided strategy to progressively assign pseudo labels to unlabeled instances with different confidence scores, which are in turn leveraged as weights to guide the optimization as training goes on. Collaborating with a simple self-mining operation, we make significant improvement in the domain adaptation tasks of re-ID. In particular, we achieve the mAP of 71.5% in the adaptation task of DukeMTMC-reID to Market1501 with one shot setting, which outperforms the state-of-arts of unsupervised domain adaptation more than 17.8%. Under the five shots setting, we achieve competitive accuracy of the fully supervised setting on Market-1501. Code will be made available.

Inverse design is an outstanding challenge in disordered systems with multiple length scales such as polymers, particularly when designing polymers with desired phase behavior. We demonstrate high-accuracy tuning of poly(2-oxazoline) cloud point via machine learning. With a design space of four repeating units and a range of molecular masses, we achieve an accuracy of 4 {\deg}C root mean squared error (RMSE) in a temperature range of 24-90 {\deg}C, employing gradient boosting with decision trees. The RMSE is >3x better than linear and polynomial regression. We perform inverse design via particle-swarm optimization, predicting and synthesizing 17 polymers with constrained design at 4 target cloud points from 37 to 80 {\deg}C. Our approach challenges the status quo in polymer design with a machine learning algorithm, that is capable of fast and systematic discovery of new polymers.

When U.N. member states unanimously adopted the 2030 Agenda in 2015, the narrative around global development embraced a new paradigm of sustainability and inclusion--of planetary stewardship alongside economic progress, and inclusive distribution of income. This comprehensive agenda--merging social, economic and environmental dimensions of sustainability--is not supported by current modes of data collection and data analysis, so the report of the High-Level Panel on the post-2015 development agenda called for a "data revolution" to empower people through access to information.1 Today, a central development problem is that high-quality, timely, accessible data are absent in most poor countries, where development needs are greatest. In a world of unequal distributions of income and wealth across space, age and class, gender and ethnic pay gaps, and environmental risks, data that provide only national averages conceal more than they reveal. This paper argues that spatial disaggregation and timeliness could permit a process of evidence-based policy making that monitors outcomes and adjusts actions in a feedback loop that can accelerate development through learning. Big data and artificial intelligence are key elements in such a process. Emerging technologies could lead to the next quantum leap in (i) how data is collected; (ii) how data is analyzed; and (iii) how analysis is used for policymaking and the achievement of better results. Big data platforms expand the toolkit for acquiring real-time information at a granular level, while machine learning permits pattern recognition across multiple layers of input. Together, these advances could make data more accessible, scalable, and finely tuned. In turn, the availability of real-time information can shorten the feedback loop between results monitoring, learning, and policy formulation or investment, accelerating the speed and scale at which development actors can implement change.