As part of the CleanTechnica series on the use of machine learning in advancing our low-carbon future, it would be remiss to not point out the carbon debt. However, it's not as bad as was reported earlier this year, in my estimation. Let's talk about the study itself, and the assumptions it made. The paper that made some headlines was Energy and Policy Considerations for Deep Learning in NLP by Strubell, Ganesh, and McCallum of the University of Massachusetts Amherst, and it was published in June of 2019. Strubell and McCallum are part of the team that built a state-of-the-art natural language processing model, LISA.

Information regarding the location of power distribution grid can be extracted from the power signature embedded in the multimedia signals (e.g., audio, video data) recorded near electrical activities. This implicit mechanism of identifying the origin-of-recording can be a very promising tool for multimedia forensics and security applications. In this work, we have developed a novel grid-of-origin identification system from media recording that consists of a number of support vector machine (SVM) followed by pole-matching (PM) classifiers. First, we determine the nominal frequency of the grid (50 or 60 Hz) based on the spectral observation. Then an SVM classifier, trained for the detection of a grid with a particular nominal frequency, narrows down the list of possible grids on the basis of di ff erent discriminating features extracted from the electric network frequency (ENF) signal. The decision of the SVM classifier is then passed to the PM classifier that detects the final grid based on the minimum distance between the estimated poles of test and training grids. Thus, we start from the problem of classifying grids with di fferent nominal frequencies and simplify the problem of classification in three stages based on nominal frequency, SVM and finally using PM classifier. This cascaded system of classification ensures better accuracy (15 .57% Keywords: Location forensics, ENF, nominal frequency, SVM, AR model, pole-matching classifier. 1. Introduction With the proliferation of terrorism, child pornography [1] or abuse on women, location forensics has become an important area of research in the 21 Success in identifying such locations properly can ease the process of getting hold of the criminals involved.

At high latitudes, many cities adopt a centralized heating system to improve the energy generation efficiency and to reduce pollution. In multi-tier systems, so-called district heating, there are a few efficient approaches for the flow rate control during the heating process. In this paper, we describe the theoretical methods to solve this problem by deep reinforcement learning and propose a cloud-based heating control system for implementation. A real-world case study shows the effectiveness and practicability of the proposed system controlled by humans, and the simulated experiments for deep reinforcement learning show about 1985.01 gigajoules of heat quantity and 42276.45 tons of water are saved per hour compared with manual control.

A total of 3,400 people lost their lives and 14,670 were injured in fires in the USA in 2017, a 9.6 percent increase over the 2007 casualty rate. Floods meanwhile killed more than 100 Americans last year, a number that has also been increasing. To counter this terrible toll, artificial intelligence researchers are developing systems to improve disaster prediction accuracy and provide timely evacuation guidance for panicked people during emergencies. Providing real-time evacuation strategies is critical, as research shows that in emergencies many people tend to wait for instructions when they should already be proceeding to an exit. Simulation systems can play a valuable role in identifying and testing evacuation plans to enable individuals to promptly leave a dangerous area via the safest and fastest route.

"Time series models are used to forecast future events based on previous events that have been observed (and data collected) at regular time intervals." We will be taking a small forecasting problem and try to solve it till the end learning time series forecasting alongside. Time series forecasting is a technique for the prediction of events through a sequence of time. The technique is used across many fields of study, from geology to behavior to economics. The techniques predict future events by analyzing the trends of the past, on the assumption that future trends will hold similar to historical trends.

We've all tried Google Street View before, but what if you could explore the world and see faraway places through the eyes of a roving machine? At the recent Combined Exhibition of Advanced Technologies (CEATEC) outside Tokyo, telepresence robots equipped with displays showing their remote users were turning heads on the show floor. These simple machines are basically webcams on wheels, but they formed a striking example of how a system that combines hardware in the physical world with online users and cloud-based artificial intelligence will become part of everyday life. Akira Fukabori, director of ANA HOLDINGS INC.'s Avatar Division, shows off an all-terrain Avatar robot at CEATEC 2019. Developed by OhmniLabs and ANA HOLDINGS INC., the parent company of All Nippon Airways, the newme Avatar telepresence robots are up to 150 cm tall and roll around on a wheeled base at speeds up to 2.9 kph.

With the help of machine learning and artificial intelligence researchers are accelerating the power of batteries. Researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory have turned to the power of machine learning and artificial intelligence to dramatically accelerate the process of battery discovery, according to the study published in -- Chemical Science. As described in two new papers, Argonne researchers first created a highly accurate database of roughly 133,000 small organic molecules that could form the basis of battery electrolytes. To do so, they used a computationally intensive model called G4MP2. This collection of molecules, however, represented only a small subset of 166 billion larger molecules that scientists wanted to probe for electrolyte candidates.

Junning Huang* 1, Sirui Xie* 2, Jiankai Sun 4, Qiurui Ma 3, Chunxiao Liu 1, Jianping Shi 1, Dahua Lin 4, Bolei Zhou 4 Abstract -- Classical autonomous driving systems are mod-ularized as a pipeline of perception, decision, planning, and control. The driving decision plays a central role in processing the observation from the perception as well as directing the execution of downstream planning and control modules. Commonly the decision module is designed to be rule-based and is difficult to learn from data. Recently end-to-end neural control policy has been proposed to replace this pipeline, given its generalization ability. However, it remains challenging to enforce physical or logical constraints on the decision to ensure driving safety and stability. In this work, we propose a hybrid framework for learning a decision module, which is agnostic to the mechanisms of perception, planning, and control modules. By imitating the low-level control behavior, it learns the high-level driving decisions while bypasses the ambiguous annotation of high-level driving decisions. We demonstrate that the simulation agents with a learned decision module can be generalized to various complex driving scenarios where the rule-based approach fails. Furthermore, it can generate driving behaviors that are smoother and safer than end-to-end neural policies ‡ .

We present a learning-based force-torque dynamics to achieve model-based control for contact-rich peg-in-hole task using force-only inputs. Learning the force-torque dynamics is challenging because of the ambiguity of the low-dimensional 6-d force signal and the requirement of excessive training data. To tackle these problems, we propose a multi-pose force-torque state representation, based on which a dynamics model is learned with the data generated in a sample-efficient offline fashion. In addition, by training the dynamics model with peg-and-holes of various shapes, scales, and elasticities, the model could quickly transfer to new peg-and-holes after a small number of trials. Extensive experiments show that our dynamics model could adapt to unseen peg-and-holes with 70% fewer samples required compared to learning from scratch. Along with the learned dynamics, model predictive control and model-based reinforcement learning policies achieve over 80% insertion success rate. Our video is available at https://youtu.be/ZAqldpVZgm4.