Artificial intelligence (AI) is increasingly common in electronic devices at home or work, in social media, video streaming services, electronic commerce, and in internet search engines. Now, AI is rapidly entering the farming scene. Growers using modern precision agriculture tools and techniques often face a barrage of high data volumes created by increasingly prolific, data-hungry electronic devices and services. Compare a smart phone's data needs with an old desktop phone. Or contrast an old-style paper map of your farm with today's digital geographic information system maps, showing multiple layers of every square inch of your fields, updated every week or month by automated aerial surveys with drones.

Tokyo - When a nuclear power plant accident occurs and radioactive material is released, it is vital to evacuate people in the vicinity as quickly as possible. However, it can be difficult to immediately predict where the emitted radioactivity will settle, making it impossible to prevent the exposure of large numbers of people. A means of overcoming this difficulty has been presented in a new study reported in the journal Scientific Reports by a research team at The University of Tokyo Institute of Industrial Science. The team has created a computer program that can accurately predict where radioactive material that has been emitted will eventually land, over 30 hours in advance, using weather forecasts on the expected wind patterns. This tool enables evacuation plans and other health-protective measures to be implemented if another nuclear accident like in 2011 at the Fukushima Daiichi Nuclear Power Plant were to occur.

A means of overcoming this difficulty has been presented in a new study reported in the journal Scientific Reports by a research team at The University of Tokyo Institute of Industrial Science. The team has created a computer program that can accurately predict where radioactive material that has been emitted will eventually land, over 30 hours in advance, using weather forecasts on the expected wind patterns. This tool enables evacuation plans and other health-protective measures to be implemented if another nuclear accident like in 2011 at the Fukushima Daiichi Nuclear Power Plant were to occur. This latest study was prompted by the limitations of existing atmospheric modeling tools in the aftermath of the accident at Fukushima; tools considered so unreliable that they were not used for planning immediately after the disaster. In this context, the team created a system based on a form of artificial intelligence called machine learning, which can use data on previous weather patterns to predict the route that radioactive emissions are likely to take.

Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as Expected Improvement (EI) are significantly affected by the degree of trade-off between exploration and exploitation. Too much exploration can lead to inefficient optimization protocols, whilst too much exploitation leaves the protocol open to strong initial biases, and a high chance of getting stuck in a local minimum. Typically, a constant margin is used to control this trade-off, which results in yet another hyper-parameter to be optimized. We propose contextual improvement as a simple, yet effective heuristic to counter this - achieving a one-shot optimization strategy. Our proposed heuristic can be swiftly calculated and improves both the speed and robustness of discovery of optimal solutions. We demonstrate its effectiveness on both synthetic and real world problems and explore the unaccounted for uncertainty in the pre-determination of search hyperparameters controlling explore-exploit trade-off.

In this article, we proposed the Coopetititve Soft Gating Ensemble or CSGE for general machine learning tasks. The goal of machine learning is to create models which poses a high generalisation capability. But often problems are too complex to be solved by a single model. Therefore, ensemble methods combine predictions of multiple models. The CSGE comprises a comprehensible combination based on three different aspects relating to the overall global historical performance, the local-/situation-dependent and time-dependent performance of its ensemble members. The CSGE can be optimised according to arbitrary loss functions making it accessible for a wider range of problems. We introduce a novel training procedure including a hyper-parameter initialisation at its heart. We show that the CSGE approach reaches state-of-the-art performance for both classification and regression tasks. Still, the CSGE allows to quantify the influence of all base estimators by means of the three weighting aspects in a comprehensive way. In terms of Organic computing (OC), our CSGE approach combines multiple base models towards a self-organising complex system. Moreover, we provide a scikit-learn compatible implementation.

Canada was the business world's best-kept secret. Progress and innovation in Canada -- especially in artificial intelligence, clean technology and health care -- has been monumental for decades. Yet, we stayed humble through those years of innovation. That is, until the country embraced its position as a destination for commercial investment and a world leader in artificial intelligence. Now, Canada is empowering new companies to compete on the global stage, hosting massive technology industry events featuring the world's best innovators and attracting international talent to work on world-changing innovations.

Around the time I turned 40, I decided to address the trifecta of concerns I had about climate change, animal rights, and my health: I went hard vegan. My doctor had been warning me to cut down on red meat, and I had also moved to a rural Japanese farming village populated by farmers growing a wide variety of veggies. After a while, the euphoria wore off and the culinary limitations of vegan food, especially when traveling, became challenging. I joined the legions of ex-vegans to become a cheating pescaterian. Five years later, the great Tohoku earthquake of 2011 hit Japan, dumping a pile of radioactive cesium-137 on top of our organic garden and shattering the wonderful organic loop we had created.

In a recent discussion paper, NITI Aayog has chalked out an ambitious strategy for India to become an artificial intelligence (AI) powerhouse. AI is the use of computers to make decisions that are normally made by humans. Many forms of AI surround Indians already, including chatbots on retail websites and programs that flag fraudulent bank activity. But NITI Aayog envisions AI solutions for India on a scale not seen anywhere in the world today, especially in five key sectors -- agriculture, healthcare, education, smart cities and infrastructure, and transport. In agriculture, for example, machines will provide information to farmers on the quality of soil, when to sow, where to spray herbicide, and when to expect pest infestations.

Task offloading is an emerging technology in fog-enabled networks. It allows users to transmit tasks to neighbor fog nodes so as to utilize the computing resources of the networks. In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model. We consider the fact that different helper nodes prefer different kinds of tasks. Further, we assume each helper node just feeds back one-bit information to the task node to indicate the level of happiness. The key challenge of this problem lies in the exploration-exploitation tradeoff. We thus implement a UCB-type algorithm to maximize the long-term happiness metric. Numerical simulations are given in the end of the paper to corroborate our strategy.

This blog offers a deeper dive into the machine learning training process for performing automatic target detection. Samples of automatic target detection were recently presented at the Machine Learning: Automate Remote Sensing Analytics to Gain a Competitive Advantage webinar. Machine learning (ML) applications, from object recognition and caption generation, to automatic language translation and driverless cars, have increased dramatically over the last few years, powered mainly by the increase of computing power (using GPUs), reduced cost of storage, wider availability of training data, and development of new training techniques for the machine learning models. In the last five years, Harris Corporation has made a multi-million dollar investment into applying machine learning to solve customer challenges using remote sensing data. In response to the increased interest from our customers in evaluating how machine learning can solve their problems using geospatial data, I set out to train some of my coworkers on how to build a ML model to perform automatic feature detection on 2D overhead imagery.