The recent progress on capsule networks by Hinton et al. has generated considerable excitement in the machine learning community. The idea behind a capsule is inspired by a cortical minicolumn in the brain, whereby a vertically organised group of around 100 neurons receive common inputs, have common outputs, are interconnected, and may well constitute a fundamental computation unit of the cerebral cortex. However, Hinton's paper on "Matrix Capsule with EM Routing'" was unfortunately not accompanied by a release of source code, which left interested researchers attempting to implement the architecture and reproduce the benchmarks on their own. This has certainly slowed the progress of research building on this work. While writing our own implementation, we noticed several common mistakes in other open source implementations that we came across. In this paper we share some of these learnings, specifically focusing on three implementation pitfalls and how to avoid them: (1) parent capsules with only one child; (2) normalising the amount of data assigned to parent capsules; (3) parent capsules at different positions compete for child capsules. While our implementation is a considerable improvement over currently available implementations, it still falls slightly short of the performance reported by Hinton et al. (2018). The source code for this implementation is available on GitHub at the following URL: https://github.com/IBM/matrix-capsules-with-em-routing.

We will work together to foster global economic growth, while harnessing the power of technological innovation, in particular digitalization, and its application for the benefit of all. We are resolved to build a society capable of seizing opportunities, and tackling economic, social and environmental challenges, presented today and in the future, including those of demographic change. This recovery is supported by the continuation of accommodative financial conditions and stimulus measures taking effect in some countries. However, growth remains low and risks remain tilted to the downside. Most importantly, trade and geopolitical tensions have intensified. We will continue to address these risks, and stand ready to take further action. Fiscal policy should be flexible and growth-friendly while rebuilding buffers where needed and ensuring debt as a share of GDP is on a sustainable path. Monetary policy will continue to support economic activity and ensure price stability, consistent with central banks' mandates. Central bank decisions need to remain well communicated.

Neural networks are behind technologies that are revolutionizing our daily lives, such as face recognition, web searching, and medical diagnosis. These general problem solvers reach their solutions by being adapted or "trained" to capture correlations in real-world data. Having seen the success of neural networks, physicists are asking if the tools might also be useful in areas ranging from high-energy physics to quantum computing [1]. Four research groups now report on using neural network tools to tackle one of the most computationally challenging problems in condensed-matter physics--simulating the behavior of an open many-body quantum system [2–5]. This scenario describes a collection of particles--such as the qubits in a quantum computer--that both interact with each other and exchange energy with their environment.

If you've ever attended an AI conference, I bet you passed under the placid gaze of a chrome-plated humanoid, lovingly selected from an ocean of creepy robot stock images that marketing teams can't resist pasting on every billboard these days. Clearly, I'm personally guilty of using octarine-blue sci-fi art to lure weary travelers to my blog. It certainly works, which is why it's a pity that those images have next to nothing to do with AI. You'd think we'd all be more ashamed of ourselves, but don't worry, AI is too useful to go away, no matter how much we all cry wolf. Marketing folk run around trying to get your attention with sci-fi gimmicks, but the reason you'll stick around long enough to buy into AI is entirely different.

Rapid advances in computing and robotics have led to calls for government controls. Before acting, we need to distinguish among the many meanings and applications of the technology. New technologies often spur public anxiety, but the intensity of concern about the implications of advances in artificial intelligence (AI) is particularly noteworthy. Several respected scholars and technology leaders warn that AI is on the path to turning robots into a master class that will subjugate humanity, if not destroy it. Others fear that AI is enabling governments to mass produce autonomous weapons--"killing machines"--that will choose their own targets, including innocent civilians. Renowned economists point out that AI, unlike previous technologies, is destroying many more jobs than it creates, leading to major economic disruptions. There seems to be widespread agreement that AI growth is accelerating.

Interaction function (IFC), which captures interactions among items and users, is of great importance in collaborative filtering (CF). The inner product is the most popular IFC due to its success in low-rank matrix factorization. However, interactions in real-world applications can be highly complex. Many other operations (such as plus and concatenation) have also been proposed, and can possibly offer better performance than the inner product. In this paper, motivated by the success of automated machine learning, we propose to search for proper interaction functions (SIF) for CF tasks. We first design an expressive search space for SIF by reviewing and generalizing existing CF approaches. We then propose to represent the search space as a structured multi-layer perceptron, and design a stochastic gradient descent algorithm which can simultaneously update both architectures and learning parameters. Experimental results demonstrate that the proposed method can be much more efficient than popular AutoML approaches, and also obtain much better prediction performance than state-of-the-art CF approaches.

Matrix factorization methods are extensively employed to understand complex data. In this paper, we introduce the cross-product penalized component analysis (XCAN), a sparse matrix factorization based on the optimization of a loss function that allows a trade-off between variance maximization and structural preservation. The approach is based on previous developments, notably (i) the Sparse Principal Component Analysis (SPCA) framework based on the LASSO, (ii) extensions of SPCA to constrain both modes of the factorization, like co-clustering or the Penalized Matrix Decomposition (PMD), and (iii) the Group-wise Principal Component Analysis (GPCA) method. The result is a flexible modeling approach that can be used for data exploration in a large variety of problems. We demonstrate its use with applications from different disciplines.

The prediction of stock prices is an important task in economics, investment and financial decision-making. It has for several decades, spurred the interest of many researchers to design stock price predictive models. In this paper, the symbiotic organisms search algorithm, a new metaheuristic algorithm is employed as an efficient method for training feedforward neural networks (FFNN). The training process is used to build a better stock price predictive model. The Straits Times Index, Nikkei 225, NASDAQ Composite, S&P 500, and Dow Jones Industrial Average indices were utilized as time series data sets for training and testing proposed predic-tive model. Three evaluation methods namely, Root Mean Squared Error, Mean Absolute Percentage Error and Mean Absolution Deviation are used to compare the results of the implemented model. The computational results obtained revealed that the hybrid Symbiotic Organisms Search Algorithm exhibited outstanding predictive performance when compared to the hybrid Particle Swarm Optimization, Genetic Algorithm, and ARIMA based models. The new model is a promising predictive technique for solving high dimensional nonlinear time series data that are difficult to capture by traditional models.

Roughly half of the 821 million people considered hungry by the United Nations are those who dedicate their lives to producing food for others: farmers. This is largely attributed to the vulnerability of farmers to agricultural risks, such as extreme weather, conflict, and market shocks. Smallholder farmers, who produce some 60-70% of the world's food, are particularly vulnerable to risks and food insecurity. Emerging technologies such as Artificial Intelligence (AI), however, have been particularly promising in tackling challenges such as lack of expertise, climate change, resource optimization and consumer trust. AI assistance can, for instance, enable smallholder farmers in Africa to more effectively address scourges such as viruses and the fall armyworm that have plagued the region over the last 40 years despite extensive investment, said David Hughes, Co-Founder of PlantVillage and Assistant Professor at Penn State University at a session on AI for Agriculture at last week's AI for Good Global Summit.

We present RUSLAN -- a new open Russian spoken language corpus for the text-to-speech task. RUSLAN contains 22200 audio samples with text annotations -- more than 31 hours of high-quality speech of one person -- being the largest annotated Russian corpus in terms of speech duration for a single speaker. We trained an end-to-end neural network for the text-to-speech task on our corpus and evaluated the quality of the synthesized speech using Mean Opinion Score test. Synthesized speech achieves 4.05 score for naturalness and 3.78 score for intelligibility on a 5-point MOS scale.