A measure of relative importance of variables is often desired by researchers when the explanatory aspects of econometric methods are of interest. To this end, the author briefly reviews the limitations of conventional econometrics in constructing a reliable measure of variable importance. The author highlights the relative stature of explanatory and predictive analysis in economics and the emergence of fruitful collaborations between econometrics and computer science. Learning lessons from both, the author proposes a hybrid approach based on conventional econometrics and advanced machine learning (ML) algorithms, which are otherwise, used in predictive analytics. The purpose of this article is two-fold, to propose a hybrid approach to assess relative importance and demonstrate its applicability in addressing policy priority issues with an example of food inflation in India, followed by a broader aim to introduce the possibility of conflation of ML and conventional econometrics to an audience of researchers in economics and social sciences, in general.

We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores. For this purpose, we study different models of hyperbolic space and find that learning embeddings in the Lorentz model is substantially more efficient than in the Poincar\'e-ball model. We show that the proposed approach allows us to learn high-quality embeddings of large taxonomies which yield improvements over Poincar\'e embeddings, especially in low dimensions. Lastly, we apply our model to discover hierarchies in two real-world datasets: we show that an embedding in hyperbolic space can reveal important aspects of a company's organizational structure as well as reveal historical relationships between language families.

The Department of Energy pulled back the curtain on the world's most powerful supercomputer Friday. When Summit is operating at max capacity, it can run at 200 petaflops -- that's 200 quadrillion calculations per second. That smokes the previous record holder, China's Sunway TaihuLight (which has a 93 petaflop capacity). Summit is also about seven times faster than Titan, the previous US record holder which is housed at the same Oak Ridge National Lab in Tennessee. For perspective, in one hour, Summit can solve a problem that it would take a desktop computer 30 years to crack.

Brazilian startup Cobli has specialized in technological solutions for vehicle fleet monitoring and management. It is currently focusing on safety and refining a tool to identify driver behavioral patterns by analyzing data collected by a solar-powered tracker. The project is based on machine learning, an application of artificial intelligence, and had the support) from the São Paulo Research Foundation - FAPESP through its Innovative Research in Small Business Program (PIPE http://www.bv.fapesp.br/en/3). "The algorithm uses the data collected to establish a driving profile with more than 90% accuracy," says engineer Rodrigo Mourad, a partner and co-founder of Cobli. According to Mourad, in one or two weeks of use, the system can glean a sufficient amount of data - on speed, acceleration, braking and curve angles - to produce a profile of the driver's vehicle handling habits.

Artificial Intelligence, or AI, is hot topic these days. Along with robotics and automation, depending on who you listen to AI is either the most wonderful or most disastrous development in human history. Will AI take your job away? Will it free you from boring or dangerous tasks so you can enjoy life? Will it lead to World War III or a Star Trek like Utopia?

If the robotics world had a celebrity it would be Spot Mini of Boston Dynamics. Last month at the Robotics Summit in Boston the mechanical dog strutted onto the floor of the Westin Hotel trailed by hundreds of flickering iPhones. Marc Raibert first unveiled his metal menaagerie almost a decade ago with a video of Big Dog. Today, Mini is the fulfillment of his mission in a sleeker, smarter, and environmentally friendlier robo-canine package than its gas-burning ancestor. Since the early 1990s, machines have relied on rechargeable lithium ion batteries for power.

A golden eagle is seen flying over a wind turbine wind farm in Wyoming. Maybe not as many as some opponents would have you believe, but it's a problem for the renewable energy industry (along with improper siting in bird flight paths). Of course, coal-fired energy in the United States kills birds too. Eagles, also a symbol of America, hold a special place in the wildlife world. They're protected by federal law, and certainly worth protecting from the whooshing blades of wind turbines.

To get a sense of the extent to which drones have captured the public imagination, look to the skies. In Folsom, Calif., more than 950 drones took to the skies earlier this month to create a glowing, real-world version of Time magazine's iconic cover, hovering 400 feet above the ground. "Up in the sky, I saw the future," a local resident told a local news station. In recent years, there have been no shortage of publicity-grabbing announcements involving unmanned aerial vehicles (UAVs)--just consider Amazon's headline-grabbing goal of drone-delivered packages. But reality is catching up with these long-stated aspirations and, through a combination of drone-friendly legislation and practical research, Virginia is poised to become a key player in determining how to make day-to-day drone operations a reality in a wide range of sectors.

We revisit the importance of the individual units in Convolutional Neural Networks (CNNs) for visual recognition. By conducting unit ablation experiments on CNNs trained on large scale image datasets, we demonstrate that, though ablating any individual unit does not hurt overall classification accuracy, it does lead to significant damage on the accuracy of specific classes. This result shows that an individual unit is specialized to encode information relevant to a subset of classes. We compute the correlation between the accuracy drop under unit ablation and various attributes of an individual unit such as class selectivity and weight L1 norm. We confirm that unit attributes such as class selectivity are a poor predictor for impact on overall accuracy as found previously in recent work \cite{morcos2018importance}. However, our results show that class selectivity along with other attributes are good predictors of the importance of one unit to individual classes. We evaluate the impact of random rotation, batch normalization, and dropout to the importance of units to specific classes. Our results show that units with high selectivity play an important role in network classification power at the individual class level. Understanding and interpreting the behavior of these units is necessary and meaningful.

Deep neural network models are usually trained in cluster environments, where the model parameters are iteratively refined by multiple worker machines in parallel. One key challenge in this regard is the presence of stragglers, which significantly degrades the learning performance. In this paper, we propose to eliminate stragglers by adapting each worker's training load to its processing capability; that is, slower workers receive a smaller batch of data to process. Following this idea, we develop a new synchronization scheme called LB-BSP (Load-balanced BSP). It works by coordinately setting the batch size of each worker so that they can finish batch processing at around the same time. A prerequisite for deciding the workers' batch sizes is to know their processing speeds before each iteration starts. For the best prediction accuracy, we adopt NARX, an extended recurrent neural network that accounts for both the historical speeds and the driving factors such as CPU and memory in prediction. We have implemented LB-BSP for both TensorFlow and MXNet. EC2 experiments against popular benchmarks show that LB-BSP can effectively accelerate the training of deep models, with up to 2x speedup.