After the tremendous success of convolutional neural networks in image classification, object detection, speech recognition, etc., there is now rising demand for deployment of these compute-intensive ML models on tightly power constrained embedded and mobile systems at low cost as well as for pushing the throughput in data centers. This has triggered a wave of research towards specialized hardware accelerators. Their performance is often constrained by I/O bandwidth and the energy consumption is dominated by I/O transfers to off-chip memory. We introduce and evaluate a novel, hardware-friendly compression scheme for the feature maps present within convolutional neural networks. We show that an average compression ratio of 4.4x relative to uncompressed data and a gain of 60% over existing method can be achieved for ResNet-34 with a compression block requiring <300 bit of sequential cells and minimal combinational logic.

We present an approach based on machine learning (ML) to distinguish eruption and precursory signals of Chimay\'{o} geyser (New Mexico, USA) under noisy environments. This geyser can be considered as a natural analog of $\mathrm{CO}_2$ intrusion into shallow water aquifers. By studying this geyser, we can understand upwelling of $\mathrm{CO}_2$-rich fluids from depth, which has relevance to leak monitoring in a $\mathrm{CO}_2$ sequestration project. ML methods such as Random Forests (RF) are known to be robust multi-class classifiers and perform well under unfavorable noisy conditions. However, the extent of the RF method's accuracy is poorly understood for this $\mathrm{CO}_2$-driven geysering application. The current study aims to quantify the performance of RF-classifiers to discern the geyser state. Towards this goal, we first present the data collected from the seismometer that is installed near the Chimay\'{o} geyser. The seismic signals collected at this site contain different types of noises such as daily temperature variations, seasonal trends, animal movement near the geyser, and human activity. First, we filter the signals from these noises by combining the Butterworth-Highpass filter and an Autoregressive method in a multi-level fashion. We show that by combining these filtering techniques, in a hierarchical fashion, leads to reduction in the noise in the seismic data without removing the precursors and eruption event signals. We then use RF on the filtered data to classify the state of geyser into three classes -- remnant noise, precursor, and eruption states. We show that the classification accuracy using RF on the filtered data is greater than 90\%.These aspects make the proposed ML framework attractive for event discrimination and signal enhancement under noisy conditions, with strong potential for application to monitoring leaks in $\mathrm{CO}_2$ sequestration.

Cyber-physical systems (CPSs) embed software into the physical world. They appear in a wide range of applications such as smart grids, robotics, intelligent manufacture and medical monitoring. CPSs have proved resistant to modeling due to their intrinsic complexity arising from the combination of physical components and cyber components and the interaction between them. This study proposes a general framework for reverse engineering CPSs directly from data. The method involves the identification of physical systems as well as the inference of transition logic. It has been applied successfully to a number of real-world examples ranging from mechanical and electrical systems to medical applications. The novel framework seeks to enable researchers to make predictions concerning the trajectory of CPSs based on the discovered model. Such information has been proven essential for the assessment of the performance of CPS, the design of failure-proof CPS and the creation of design guidelines for new CPSs.

This post was done in partnership with Wirecutter. When readers choose to buy Wirecutter's independently chosen editorial picks, Wirecutter and Engadget may earn affiliate commission. Although flying a drone might sound like the biggest risk in operating one, dealing with the batteries is potentially more explosive. At the 100 hospital emergency rooms that report electronics-related injury cases to the US Consumer Product Safety Commission, more than 200 incidents (PDF) involving drone batteries, stemming from fire, smoke, and explosions, were recorded between 2012 and 2017. Not every drone-battery incident results in an injury, but each pilot and expert I interviewed had a story about an exploding or fiery lithium battery going off especially after it had repeatedly crashed to the ground inside a drone.

Software defined networking (SDN) represents a promising networking architecture that combines central management and network programmability. SDN separates the control plane from the data plane and moves the network management to a central point, called the controller, that can be programmed and used as the brain of the network. Recently, the research community has showed an increased tendency to benefit from the recent advancements in the artificial intelligence (AI) field to provide learning abilities and better decision making in SDN. In this study, we provide a detailed overview of the recent efforts to include AI in SDN. Our study showed that the research efforts focused on three main sub-fields of AI namely: machine learning, meta-heuristics and fuzzy inference systems. Accordingly, in this work we investigate their different application areas and potential use, as well as the improvements achieved by including AI-based techniques in the SDN paradigm.

The world as we know it will change profoundly over the next ten years. With a projected global population of over 8.4 billion by 2028, businesses across all industries are investing billions of dollars in technology and innovation in order to be successful in a future where everyone is connected and information is instant. By 2025, it is estimated that nearly 8 billion people will be "hyper-connected" (instant access to information) through telecommunication and the internet, a huge increase over the current 3 billion.Shutterstock With countries imposing bans on fossil fuels, the continued looming threat of cyber-attacks, and many professions being forever reshaped due to improvements in technology; change is inevitable. Our society is advancing faster than ever before, and businesses across the globe are implementing strategies today to fulfill the needs of the future.

My colleagues and I had the privilege of attending Tata Consultancy Services' (TCS) Analyst Day event held in Boston on September 7, 2018. There were several interesting and informative presentations covering the concepts of Business 4.0 and MachineFirst Philosophy and how TCS is leveraging its unparalleled domain expertise and its deep and vast portfolio of services and solutions to provide its customers with exponential value to create abundance through mass customization, leveraging ecosystems to help its customers embrace and manage risk while maximizing business outcomes using technologies and concepts such as Cloud, Intelligence, Automated and Agile. As one of the ARC Analysts focused on upstream and midstream oil & gas it was great to learn more about how TCS is leveraging'cognitive automation' through its solutions such as Ignio, an product that provides some very powerful horsepower through its self-learning capability, empowered by machine learning and artificial intelligence (AI), that can move customers from predictive maintenance to prescriptive maintenance, thereby extending the life (and availability) of an asset such as a pump or compressor and also optimizing that asset's performance and the process for which it is being utilized. MachineFirst Philosophy creates exponential value by empowering enterprise agility through reimagination and reinvention of a company's DNA. Harrick Vin, Vice President & Global Head of Ignio, explained that he envisions cognitive computing platforms such as Ignio, the Intelligent Machine", as being technology that is being augmented by people and one that is capable of learning over time.

A computer graphic image provided by Japan's space agency shows two drum-shaped and solar-powered rovers on an asteroid. A Japanese unmanned spacecraft released two small rovers on the asteroid Ryugu last week. A computer graphic image provided by Japan's space agency shows two drum-shaped and solar-powered rovers on an asteroid. A Japanese unmanned spacecraft released two small rovers on the asteroid Ryugu last week. Want to see what it would be like to stand on a asteroid? Well, if you were not a human but rather a seven-inch-diameter, just under 3-inch-tall, hopping robot?

As a tech geek and writer for an IT company, I love having discussions about things like Blockchain and AI -- and their impact on our current and future lives -- with my layman best friend (who works in Public Security). He's still waiting for the day I show up at his house in a fully operating Iron Man-like flight suit. I still believe that one day I will. A while ago, we had a very interesting discussion about AI and intelligent systems in general, which reminded me how important it is to regularly talk to people outside of your field of work, to gain new insights. I realize that my friend was intuitively meshing his definition of'Intelligence' with a vague notion of Free Will, which I find to be a strong and useful intuition. The discussion also led me to want to have a better understanding of the current developments in applied Artificial Intelligence in the world, so as to be able to make a better informed prediction of its future.

A consortium of universities, research laboratories and industry partners will take a $20 million grant from the National Science Foundation to modernize the state's century-old electrical grid. Announced by lawmakers on Friday, the grant will fund a SMART Grid Center at the University of New Mexico -- it's not a physical building, but a "novel, interdisciplinary research center that will address pressing design, operational, data, and security challenges of next-generation electric power management," said William Michener, principal investigator for the award. Michener is also the state director of New Mexico's Established Program to Stimulate Competitive Research, or EPSCoR, program, which is directed at jurisdictions traditionally underfunded in research grants. The SMART Grid Center -- which stands for Sustainable, Modular, Adaptive, Resilient and Transactive -- has four main research objectives: improving the resilience and cybersecurity of the grid, utilizing machine-learning algorithms to optimize power production and building in simulations and testbed systems to validate performance and sustainability. The fourth and most comprehensive objective will be to adapt the existing electrical infrastructure to accept wind, solar and other new forms of energy, without a noticeable decrease in supply.