It began, late last year, with Silver boasting about the success of his election models and Taleb shooting back that Silver doesn't "know how math works." Silver said Taleb was "consumed by anger" and hadn't had any new ideas since 2001. The argument has gotten personal, with Silver calling Taleb an "intellectual-yet-idiot" (an insult taken from Taleb's own book) and Taleb calling Silver "klueless" and "butthurt." Here is a recap of what they're fighting about so you can know who's right (Silver, mostly) and who's wrong (Taleb). The origin of Taleb's ire can be found in Silver's success since 2008--and his some-time failures. As I described in Nautilus last month, evaluating probabilistic election forecasts can be conceptually slippery, made especially difficult by the counterintuitive properties of mathematical probability.

Finding the source of a disturbance or fault in complex systems such as industrial chemical processing plants can be a difficult task and consume a significant number of engineering hours. In many cases, a systematic elimination procedure is considered to be the only feasible approach but can cause undesired process upsets. Practitioners desire robust alternative approaches. This paper presents an unsupervised, data-driven method for ranking process elements according to the magnitude and novelty of their influence. Partial bivariate transfer entropy estimation is used to infer a weighted directed graph of process elements. Eigenvector centrality is applied to rank network nodes according to their overall effect. As the ranking of process elements rely on emerging properties that depend on the aggregate of many connections, the results are robust to errors in the estimation of individual edge properties and the inclusion of indirect connections that do not represent the true causal structure of the process. A monitoring chart of continuously calculated process element importance scores over multiple overlapping time regions can assist with incipient fault detection. Ranking results combined with visual inspection of information transfer networks is also useful for root cause analysis of known faults and disturbances. A software implementation of the proposed method is available.

Businesses and nonprofits are finding novel ways to employ artificial intelligence in the developing world, using the tools to improve agriculture yields, infant health care, and entrepreneur earnings, according to speakers at MIT Technology Review's EmTech Digital conference in San Francisco on Tuesday. Solomon Assefa, who oversees IBM's research labs in Kenya and South Africa, said the company has been using AI to more accurately predict crop yields in specific regions, based on shifting weather patterns, soil moisture, and other conditions. This insight into growing conditions has helped local farmers raise financing to expand their operations, or make better decisions about the right seeds, appropriate fertilizer, and ideal times to plant and harvest. Separately, the tech giant's research lab has partnered with a startup, Hello Tractor, that links farmers in need of tractors with owners looking to lease equipment. By forecasting demand for the vehicles, IBM has also helped owners raise money to expand their fleet, boosting their profits, Assefa said.

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 15 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

A Dutch inventor has developed a'cow toilet' to help cut ammonia emissions from cow urine that cause environmental pollution. Tests on the device, which collects around 26 to 35 pints (15 to 20 litres) of urine produced daily by a single cow, have started on a farm in the country. Inventor Henk Hanskamp claims the device could halve the ammonia emissions from cows, which account for almost half (49 per cent) of agricultural ammonia pollution. This type of contamination has multiple negative impacts on both the environment and human health and can threaten aquatic wildlife and contribute to smog. The small-scale tests are being conducted in the Netherlands, the world's second-biggest agricultural exporter behind the United States.

Electronic Medical Records (EMR) are a rich source of patient information, including measurements reflecting physiologic signs and administered therapies. Identifying which variables are useful in predicting clinical outcomes can be challenging. Advanced algorithms such as deep neural networks were designed to process high-dimensional inputs containing variables in their measured form, thus bypass separate feature selection or engineering steps. We investigated the effect of extraneous input variables on the predictive performance of Recurrent Neural Networks (RNN) by including in the input vector extraneous variables randomly drawn from theoretical and empirical distributions. RNN models using different input vectors (EMR variables; EMR and extraneous variables; extraneous variables only) were trained to predict three clinical outcomes: in-ICU mortality, 72-hour ICU re-admission, and 30-day ICU-free days. The measured degradations of the RNN's predictive performance with the addition of extraneous variables to EMR variables were negligible.

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.

In this study, we establish a basis for selecting similarity measures when applying machine learning techniques to solve materials science problems. This selection is considered with an emphasis on the distinctiveness between materials that reflect their nature well. We perform a case study with a dataset of rare-earth transition metal crystalline compounds represented using the Orbital Field Matrix descriptor and the Coulomb Matrix descriptor. We perform predictions of the formation energies using k-nearest neighbors regression, ridge regression, and kernel ridge regression. Through detailed analyses of the yield prediction accuracy, we examine the relationship between the characteristics of the material representation and similarity measures, and the complexity of the energy function they can capture. Empirical experiments and theoretical analysis reveal that similarity measures and kernels that minimize the loss of materials distinctiveness improve the prediction performance.

In classification problems (i.e. when the labels Y are discrete), the scaling of the test error with respect to n is determined by characterizations of the VC-dimension [2]/Rademacher complexity [3] of the function class, which in the worst case increases with its number of parameters. In regression (i.e. when the labels Y are continuous), the mean-squared error of the ordinary least-squares estimate is characterized by the condition number of the regression matrix, which is reasonable for appropriate ratios of d/n but tends to increase astronomically as d approaches n. The qualitative fear is the same: if the function class is too complex, it starts to overfit noise and can generalize poorly to unseen test data. But there is a gap between "can" and "will" -- and indeed this conventional wisdom has been challenged by the recent advent of deeper and deeper neural networks. In particular, a thought-provoking paper [4] noted that several deep neural networks generalize well despite achieving zero or close to zero training error, and being so expressive that they even have the ability to fit pure noise. As they put it, "understanding deep learning requires rethinking generalization". How can we reconcile the fact that good interpolative solutions exist with the classical bias-variance tradeoff? These phenomena are being actively investigated in a statistical sense [5,6] and a computational sense [7-9] in classification problems and/or noiseless models.

A new host of liquid metals that have applications towards soft robotics are making movies like'The Terminator' transcend make-believe. According to researchers, experimental liquid metals like gallium and other alloys, when supplemented with nickel or iron, are able to flex and mold into shapes with the use of magnets, much like the iconic movie villain, T-1000 from'The Terminator 2: Judgement Day.' While other such metals have been developed, they contended with two major drawbacks. A new host of liquid metals that have applications towards soft robotics are making movies like'The Terminator' transcend make-believe toward real life. Researchers say experimental liquid metals like gallium and other alloys, when supplemented with nickel or iron, are able to flex and mold into shapes with the use of magnets. A new material revealed by the American Chemical Society solves to major problems experienced by similar substances.