Simulators often require calibration inputs estimated from real world data and the quality of the estimate can significantly affect simulation output. Particularly when performing simulation optimisation to find an optimal solution, the uncertainty in the inputs significantly affects the quality of the found solution. One remedy is to search for the solution that has the best performance on average over the uncertain range of inputs yielding an optimal compromise solution. We consider the more general setting where a user may choose between either running simulations or instead collecting real world data. A user may choose an input and a solution and observe the simulation output, or instead query an external data source improving the input estimate enabling the search for a more focused, less compromised solution. We explicitly examine the trade-off between simulation and real data collection in order to find the optimal solution of the simulator with the true inputs. Using a value of information procedure, we propose a novel unified simulation optimisation procedure called Bayesian Information Collection and Optimisation (BICO) that, in each iteration, automatically determines which of the two actions (running simulations or data collection) is more beneficial. Numerical experiments demonstrate that the proposed algorithm is able to automatically determine an appropriate balance between optimisation and data collection.

In this paper, we propose a machine learning approach for forecasting hierarchical time series. Rather than using historical or forecasted proportions, as in standard top-down approaches, we formulate the disaggregation problem as a non-linear regression problem. We propose a deep neural network that automatically learns how to distribute the top-level forecasts to the bottom level-series of the hierarchy, keeping into account the characteristics of the aggregate series and the information of the individual series. In order to evaluate the performance of the proposed method, we analyze hierarchical sales data and electricity demand data. Besides comparison with the top-down approaches, the model is compared with the bottom-up method and the optimal reconciliation method. Results demonstrate that our method does not only increase the average forecasting accuracy of the hierarchy but also addresses the need of building an automated procedure generating coherent forecasts for many time series at the same time.

When you think of the words "data" and "mine", no doubt the idea of data mining comes first. However, just as much as we find value in mining the rich resources of data, so too can we apply the advanced techniques for dealing with data to real-world mining -- that is, extracting natural resources from the earth. The world is just as dependent on natural resources as it is data resources, so it makes sense to see how the evolving areas of artificial intelligence and machine learning have an impact on the world of mining and natural resource extraction. Mining has always been a dangerous profession, since extracting minerals, natural gas, petroleum, and other resources requires working in conditions that can be dangerous for human life. Increasingly, we are needing to go to harsher climates such as deep under the ocean or deep inside the earth to extract the resources we still need.

Each month, Future Tense Fiction--a series of short stories from Future Tense and Arizona State University's Center for Science and the Imagination about how technology and science will change our lives--publishes a story on a theme. The evening before you sign and take delivery of your son, you call Charlie and tell him you think you've made a huge mistake. "Let me come on over and split a few with you," he says. "I haven't seen the fire pit yet." Charlie--a short, compact man with green eyes and a shaved head whom you met when he delivered groceries the first few weeks you were housebound--brings over a six-pack. You walk out into the complex's community garden together. It used to be a parking lot, and the path through the mushroom gardens under the solar panels is still faded gray asphalt and leftover white lines. You're careful with your right foot; you still haven't gotten used to the way your prosthetic moves. You and Sienna from 4B have a fire pit and stone circle dug out in your combined lots, and she's grown a privacy wall of rosebushes that surround the relaxing space. Charlie sits on one of the cedar benches as you fiddle with twigs to make a fire. This beats the awkwardness of sitting down to talk right away. Your parents didn't raise you to be direct about feelings. Neither did the army, nor the warehouse you drove a forklift in. Charlie will, if you let him. Making a fire gives you a moment to sort out all your feelings. Or maybe it just gives you an excuse to delay talking about them.

Researchers from U of T Engineering and Carnegie Mellon University are using electrolyzers like this one to convert waste CO2 into commercially valuable chemicals. Their latest catalyst, designed in part through the use of AI, is the most efficient in its class. Credit: Daria Perevezentsev / University of Toronto Engineering Researchers at University of Toronto Engineering and Carnegie Mellon University are using artificial intelligence (AI) to accelerate progress in transforming waste carbon into a commercially valuable product with record efficiency. They leveraged AI to speed up the search for the key material in a new catalyst that converts carbon dioxide (CO2) into ethylene -- a chemical precursor to a wide range of products, from plastics to dish detergent. The resulting electrocatalyst is the most efficient in its class.

Non-Intrusive Load Monitoring (NILM) or Energy Disaggregation (ED), seeks to save energy by decomposing corresponding appliances power reading from an aggregate power reading of the whole house. It is a single channel blind source separation problem (SCBSS) and difficult prediction problem because it is unidentifiable. Recent research shows that deep learning has become a growing popularity for NILM problem. The ability of neural networks to extract load features is closely related to its depth. However, deep neural network is difficult to train because of exploding gradient, vanishing gradient and network degradation. To solve these problems, we propose a sequence to point learning framework based on bidirectional (non-casual) dilated convolution for NILM. To be more convincing, we compare our method with the state of art method--Seq2point (Zhang) directly and compare with existing algorithms indirectly via two same datasets and metrics. Experiments based on REDD and UK-DALE data sets show that our proposed approach is far superior to existing approaches in all appliances.

When you think of the words "data" and "mine", no doubt the idea of data mining comes first. However, just as much as we find value in mining the rich resources of data, so too can we apply the advanced techniques for dealing with data to real-world mining -- that is, extracting natural resources from the earth. The world is just as dependent on natural resources as it is data resources, so it makes sense to see how the evolving areas of artificial intelligence and machine learning have an impact on the world of mining and natural resource extraction. Mining has always been a dangerous profession, since extracting minerals, natural gas, petroleum, and other resources requires working in conditions that can be dangerous for human life. Increasingly, we are needing to go to harsher climates such as deep under the ocean or deep inside the earth to extract the resources we still need.

Climate change is the biggest problem that the life on this planet is facing today. It will need every possible situation including technologies like Machine Learning and Artificial Intelligence. Here are 5 ways machine learning can help combat global climate change. Carbon Tracker is an independent financial think-tank working toward the UN goal of preventing new coal plants from being built by 2020. By monitoring coal plant emissions with satellite imagery, Carbon Tracker can use the information it gathers to convince the finance industry that carbon plants aren't profitable.

C-SON (centralized self-organized network) technology has been in use for a number of years to automate the configuration of a base stations, noted Jarrett's colleague, Emmanuel Lugagne-Delpon, SVP at Orange Labs Networks, and now it is being enhanced in two ways using AI capabilities (see the graphic above). The first is "predicting the evolution of the traffic of a cell and the congestion of the cell. The tool is making decisions to re-route traffic to neighbouring base stations, to help avoid congestion, improve customer service and make better use of network resources," noted Lugagne-Delpon. The second is using real-time traffic predictions to switch modules (such as antennas) off when not needed to reduce power consumption, which can cut base station energy consumption by a few per cent, stated the Orange executive. "In these instances we can close the loop – AI is not only providing data but is also taking decisions and actions and the use case is automated," he added.

Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics. One of the contributing factors that limit current robotic manipulation systems is the difficulty of precisely sensing contact forces -- sensing and reasoning about contact forces are crucial to accurately control interactions with the environment. As a step towards enabling better robotic manipulation, we introduce DIGIT, an inexpensive, compact, and high-resolution tactile sensor geared towards in-hand manipulation. DIGIT improves upon past vision-based tactile sensors by miniaturizing the form factor to be mountable on multi-fingered hands, and by providing several design improvements that result in an easier, more repeatable manufacturing process, and enhanced reliability. We demonstrate the capabilities of the DIGIT sensor by training deep neural network model-based controllers to manipulate glass marbles in-hand with a multi-finger robotic hand. To provide the robotic community access to reliable and low-cost tactile sensors, we open-source the DIGIT design at https://digit.ml/.