A popular way to estimate the causal effect of a variable x on y from observational data is to use an instrumental variable (IV): a third variable z that affects y only through x. The more strongly z is associated with x, the more reliable the estimate is, but such strong IVs are difficult to find. Instead, practitioners combine more commonly available IV candidates---which are not necessarily strong, or even valid, IVs---into a single "summary" that is plugged into causal effect estimators in place of an IV. In genetic epidemiology, such approaches are known as allele scores. Allele scores require strong assumptions---independence and validity of all IV candidates---for the resulting estimate to be reliable. To relax these assumptions, we propose Ivy, a new method to combine IV candidates that can handle correlated and invalid IV candidates in a robust manner. Theoretically, we characterize this robustness, its limits, and its impact on the resulting causal estimates. Empirically, Ivy can correctly identify the directionality of known relationships and is robust against false discovery (median effect size <= 0.025) on three real-world datasets with no causal effects, while allele scores return more biased estimates (median effect size >= 0.118).

Real-world problems such as landmine detection require multiple sources of information to reduce the uncertainty of decision-making. A novel approach to solve these problems includes distributed systems, as presented in this work based on hardware and software multi-agent systems. To achieve a high rate of landmine detection, we evaluate the performance of a trained system over the distribution of samples between training and validation sets. Additionally, a general explanation of the data set is provided, presenting the samples gathered by a cooperative multi-agent system developed for detecting improvised explosive devices. The results show that input samples affect the performance of the output decisions, and a decision-making system can be less sensitive to sensor noise with intelligent systems obtained from a diverse and suitably organised training set.

WASHINGTON, D.C.-- Today, the U.S. Department of Energy (DOE) announced a plan to provide up to $30 million for advanced research in machine learning (ML) and artificial intelligence (AI) for both scientific investigation and the management of complex systems. The initiative encompasses two separate topic areas. One topic is focused on the development of ML and AI for predictive modeling and simulation focused on research across the physical sciences. ML and AI are thought to offer promising new alternatives to traditional programming methods for computer modeling and simulation. A second topic is focused on basic ML and AI research for "decision support" in managing complex systems.

Following the great minds of machine learning can help you discover new things and deepen your knowledge. It's fascinating to learn from the best scientists. Among them, you will find influencers, teachers, business leaders, and even many more. Undeniably their expertise can help to change the world and make it a better place. On this list, you will find not only influencers but also renowned personalities from the world of Data Science.

NASA's Jet Propulsion Laboratory is seeking ideas from the public around what kind of scientific equipment they could use to outfit tiny lunar rovers to help with Artemis and other Moon missions. The call, issued via crowdsourcing platform HeroX and called'Honey, I Shrunk the NASA Payload' in a very contemporary nod to a movie that came out 31 years ago, seeks payloads with maximum dimensions of no more than 4″ x 2″, or "similar in size to a new bar of soap." NASA wants to be able to perform the kind of science that has, in the past, required large launch vehicles, large orbiters and large launch vehicles, but with much greater frequency and at much lower costs than has been possible before. In order to pave the way for long-term lunar human presence and eventual habitation, NASA says it needs "practical and affordable ways to use lunar resources," in order to defray the costs of resupply missions – already an expensive undertaking when just traveling to the International Space Station in Earth's orbit, and astronomically more so when going as far afield as the Moon . The goal is for these to be pretty much immediately available for service, with the hope that they can be shipped out to the Moon over the course of the next one to four years.

ICT industry veteran Andile Ngcaba's inq., a Pan-African digital service provider, wants to be Africa's number one artificial intelligence (AI) service provider. The company has points of contacts in 12 African cities, Johannesburg, Gaborone, Lusaka, Ndola, Blantyre, Lilongwe, Mzuzu, Lagos, Abuja, Port Harcourt, Kanu and Abidjan. It has concluded the 100% acquisition of Vodacom Business Africa's operations in Nigeria, Zambia and Cote d'Ivoire with a further planned acquisition in Cameroon pending regulatory approvals. At the time of the announcement of the transaction last June, inq. said this deals represents a significant milestone to its vision to be a leading provider of cloud and digitally based services in key markets across sub-Saharan Africa and provides additional vital assets in its build-out of a regional footprint. Today, inq. said this landmark transaction grows inq.'s regional footprint to 13 cities in 7 countries across Africa including its existing operations in Botswana, Malawi and Mozambique.

With the advent of powerful neural language models over the last few years, research attention has increasingly focused on what aspects of language they represent that make them so successful. Several testing methodologies have been developed to probe models' syntactic representations. One popular method for determining a model's ability to induce syntactic structure trains a model on strings generated according to a template then tests the model's ability to distinguish such strings from superficially similar ones with different syntax. We illustrate a fundamental problem with this approach by reproducing positive results from a recent paper with two non-syntactic baseline language models: an n-gram model and an LSTM model trained on scrambled inputs.

The proliferation and application of machine learning based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the introduction of such IDSs has also created an additional attack vector; the learning models may also be subject to cyber attacks, otherwise referred to as Adversarial Machine Learning (AML). Such attacks may have severe consequences in ICS systems, as adversaries could potentially bypass the IDS. This could lead to delayed attack detection which may result in infrastructure damages, financial loss, and even loss of life. This paper explores how adversarial learning can be used to target supervised models by generating adversarial samples using the Jacobian-based Saliency Map attack and exploring classification behaviours. The analysis also includes the exploration of how such samples can support the robustness of supervised models using adversarial training. An authentic power system dataset was used to support the experiments presented herein. Overall, the classification performance of two widely used classifiers, Random Forest and J48, decreased by 16 and 20 percentage points when adversarial samples were present. Their performances improved following adversarial training, demonstrating their robustness towards such attacks.

We propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.

Most algorithms for representation learning and link prediction in relational data have been designed for static data. However, the data they are applied to usually evolves with time, such as friend graphs in social networks or user interactions with items in recommender systems. This is also the case for knowledge bases, which contain facts such as (US, has president, B. Obama, [2009-2017]) that are valid only at certain points in time. For the problem of link prediction under temporal constraints, i.e., answering queries such as (US, has president, ?, 2012), we propose a solution inspired by the canonical decomposition of tensors of order 4. We introduce new regularization schemes and present an extension of ComplEx (Trouillon et al., 2016) that achieves state-of-the-art performance. Additionally, we propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.