Probabilistic guarantees on the prediction of data-driven classifiers are necessary to define models that can be considered reliable. This is a key requirement for modern machine learning in which the goodness of a system is measured in terms of trustworthiness, clearly dividing what is safe from what is unsafe. The spirit of this paper is exactly in this direction. First, we introduce a formal definition of {\epsilon}-Safe Decision Region, a subset of the input space in which the prediction of a target (safe) class is probabilistically guaranteed. Second, we prove that, when data come from exponential family distributions, the form of such a region is analytically determined and controllable by design parameters, i.e. the probability of sampling the target class and the confidence on the prediction. However, the request of having exponential data is not always possible. Inspired by this limitation, we developed Multi Cost SVM, an SVM based algorithm that approximates the safe region and is also able to handle unbalanced data. The research is complemented by experiments and code available for reproducibility.

A framed photograph of three men in military fatigues hangs above his desk. They're tightening straps on what first appear to be two water heaters but are, in fact, thermonuclear weapons. Resting against a nearby wall is a black-and-white print depicting the first billionth of a second after the detonation of an atomic bomb: a thousand-foot-tall ghostly amoeba. And above us, dangling from the ceiling like the sword of Damocles, is a plastic model of the Hindenburg. Depending on how you choose to look at it, Rhodes's office is either a shrine to awe-inspiring technological progress or a harsh reminder of its power to incinerate us all in the blink of an eye.

The new approach allows scientists to better understand neural network behavior. Los Alamos National Laboratory researchers have developed a novel method for comparing neural networks that looks into the "black box" of artificial intelligence to help researchers comprehend neural network behavior. Neural networks identify patterns in datasets and are utilized in applications as diverse as virtual assistants, facial recognition systems, and self-driving vehicles. "The artificial intelligence research community doesn't necessarily have a complete understanding of what neural networks are doing; they give us good results, but we don't know how or why," said Haydn Jones, a researcher in the Advanced Research in Cyber Systems group at Los Alamos. "Our new method does a better job of comparing neural networks, which is a crucial step toward better understanding the mathematics behind AI." Researchers at Los Alamos are looking at new ways to compare neural networks.

Big names in tech are collaborating with academics to develop energy-optimized machine-learning and quantum-computing systems under the MIT AI Hardware Program, an initiative announced on Tuesday. Chip makers like TSMC and Analog Devices, hardware development lab NTT Research, supplier of EUV machines ASML, and tech behemoth Amazon have signed up so far. The goal is to figure out a roadmap outlining the production of next-generation, energy-efficient hardware for AI and quantum computing in the coming decade. To this end, the research will focus on developing novel architectures and software at the heart of a range of technologies, from analog neural networks and neuromorphic computing, to hybrid-cloud computing and HPC. Designs will be tested using proofs of concept at MIT.nano, the US university's small-scale fabrication facility.

The COVID-19 pandemic has dramatically changed all of our lives -- from how we work, to how we teach our children, to how we grocery shop. As we yearn to return to normal, we're also called on to do what we can to protect ourselves, our loved ones and our communities. Los Alamos National Laboratory is no different. We have responsibilities to the nation and to the communities where we live, and we take them very seriously. As one of the largest employers in Northern New Mexico, we're doing what we can to answer the call to use our vast scientific and technical resources to help fight this disease, and protect our employees and the communities we call home. To slow the spread of the virus, we took early and aggressive measures to get as much of our workforce as possible offsite, working from home. More than 85 percent of the laboratory's workforce is teleworking. The remaining employees are onsite because they are needed to assure the safety and security of our facilities or to perform essential national security work. For those onsite, measures are in place to keep them as safe as possible following CDC guidelines.

LOS ALAMOS, N.M., Oct. 22, 2019--A probabilistic artificial intelligence computer model developed at Los Alamos National Laboratory provided the most accurate state, national and regional forecasts of the flu in 2018, beating 23 other teams in the Centers for Disease Control and Prevention's FluSight Challenge. The CDC announced the results last week. "Accurately forecasting diseases is similar to weather forecasting in that you need to feed computer models large amounts of data so they can'learn' trends," said Dave Osthus, a statistician at Los Alamos and developer of the computer model, Dante. "But it's very different because disease spread depends on daily choices humans make in their behavior--such as travel, hand-washing, riding public transportation, interacting with the healthcare system, among other things. Those are very difficult to predict."

A probabilistic artificial intelligence computer model developed at Los Alamos National Laboratory provided the most accurate state, national, and regional forecasts of the flu in 2018, beating 23 other teams in the Centers for Disease Control and Prevention's FluSight Challenge. The CDC announced the results last week. "Accurately forecasting diseases is similar to weather forecasting in that you need to feed computer models large amounts of data so they can'learn' trends," said Dave Osthus, a statistician at Los Alamos and developer of the computer model, Dante. "But it's very different because disease spread depends on daily choices humans make in their behavior--such as travel, hand-washing, riding public transportation, interacting with the healthcare system, among other things. Those are very difficult to predict."

However, I believe that the distinction of "neats" and "scruffies" raised at Cog Sci in '81 didn't define scruffies as people who built expert systems [they didn't really exist as a "real" part of MAD. Instead, I believe AI These are the researchers who read Hawkings and say "gee, if his model of the lo-23 second big bang is right, then the distribution of intergalactic gases should be relatively even. Let's go see if that's true. However, to run our experiments we'll need a more sensitive space-based sensing device, so let's work with the engineers to design one." I think one could make the case (although not from the data collected in Cohen's survey) that the two methodologies are not informed and influenced by each other to the extent they should or could be.

Hitachi Data Systems (Santa Clara, CA) has added a download microcode enhancement to its Hi-Track expert system. The enhancement will allow Hi-Track to remotely identify and solve potential problems in a customer's storage subsystem, over the telephone. AT&T Network Systems (Oklahoma, OK) has developed System Test History Analysis, an expert system to lower circuit pack repair expenditures and to isolate and resolve intermittent problems prior to shipment to customers. The system reviews the test history on multiple switching module configurations of digital telecommunications systems equipment. The embedded system analyzes the competition's prices, compares them to Alamo's, and then suggests a suitable pricing alternative.

ALAMO is a computational methodology for leaning algebraic functions from data. Given a data set, the approach begins by building a low-complexity, linear model composed of explicit non-linear transformations of the independent variables. Linear combinations of these non-linear transformations allow a linear model to better approximate complex behavior observed in real processes. The model is refined, as additional data are obtained in an adaptive fashion through error maximization sampling using derivative-free optimization. Models built using ALAMO can enforce constraints on the response variables to incorporate first-principles knowledge. The ability of ALAMO to generate simple and accurate models for a number of reaction problems is demonstrated. The error maximization sampling is compared with Latin hypercube designs to demonstrate its sampling efficiency. ALAMO's constrained regression methodology is used to further refine concentration models, resulting in models that perform better on validation data and satisfy upper and lower bounds placed on model outputs.