This paper demonstrates the systematic use of combinatorial coverage for selecting and characterizing test and training sets for machine learning models. The presented work adapts combinatorial interaction testing, which has been successfully leveraged in identifying faults in software testing, to characterize data used in machine learning. The MNIST hand-written digits data is used to demonstrate that combinatorial coverage can be used to select test sets that stress machine learning model performance, to select training sets that lead to robust model performance, and to select data for fine-tuning models to new domains. Thus, the results posit combinatorial coverage as a holistic approach to training and testing for machine learning. In contrast to prior work which has focused on the use of coverage in regard to the internal of neural networks, this paper considers coverage over simple features derived from inputs and outputs. Thus, this paper addresses the case where the supplier of test and training sets for machine learning models does not have intellectual property rights to the models themselves. Finally, the paper addresses prior criticism of combinatorial coverage and provides a rebuttal which advocates the use of coverage metrics in machine learning applications.

US Defense Secretary Lloyd Austin has issued a directive ordering the United States military to do more to protect civilians from harm in drone attacks and other combat operations. In a two-page memo to top Pentagon civilian and military officials, Austin on Thursday ordered a comprehensive overhaul of the US Defense Department's posture towards protecting civilians in conflict zones. "The protection of innocent civilians in the conduct of our operations remains vital to the ultimate success of our operations and as a significant strategic and moral imperative," the memo reads. The defence secretary asked for an action plan from the Joint Chiefs of Staff to prevent harm to civilians and improve US responses when such incidents occur. That plan is due within 90 days.

With tax season upon us, the IRS is pushing individuals to submit to facial recognition in exchange for being able to complete a range of basic tax-related activities online. The IRS has retained a private firm--ID.me The IRS is not the only government agency working with ID.me. The company claims to serve "27 states, multiple federal agencies, and over 500 name brand retailers." This is alarming for several reasons.

Massive amounts of data are being generated daily; by some accounts, a staggering 2.5 quintillion bytes of data are being created every day. In today's world, proprietary data is one of the most valuable assets organizations have, it underpins the operations, identifying ways to improve processes and increase efficiencies, it provides insights into customer information, purchasing behavior and contains supply chain information. An organization's data is one of the most crucial elements of its business, and it must be protected. Unfortunately, humans alone can't possibly manage the volumes of data on their own. Aside from that, and more importantly and frightening is how much of an organization's data is left unmonitored, with the majority of networks unprotected.

Cybersecurity is constantly changing because technology and hackers are always on the move. In the 1980s, we had antivirus software. In the 1990s, we determined rules and installed firewalls to ensure only good activity, users and traffic were allowed in our networks. By 2000, we added network intrusion detection. In 2010, we had web application firewalls and introduced second-generation WAFs. Then came the cloud and learning how to store and secure data off premises.

The US State Department has added the "threat of missile or drone attacks" to a travel advisory for the United Arab Emirates, which was already on a United States list of "do not travel" destinations due to the COVID-19 pandemic. The department added the new potential threat to its travel warning for the UAE – already at the highest, "do not travel" level – on Thursday. "The possibility of attacks affecting US citizens and interests in the Gulf and Arabian Peninsula remains an ongoing, serious concern," the Department of State said. "Rebel groups operating in Yemen have stated an intent to attack neighboring countries, including the UAE, using missiles and drones. Recent missile and drone attacks targeted populated areas and civilian infrastructure."

Eric McCarter remembers the first time he operated a forklift truck in France--while sitting behind a desk in California. McCarter used the forklift to move a stack of pallets into a waiting truck using a setup resembling a video gaming rig. He sat behind a steering wheel and pedals that transmitted commands to the forklift thousands of miles away; large screens offered views in front, behind, and to the sides of the vehicle. The vehicle relies on limited artificial intelligence to avoid obstacles and safely come to a stop if the connection between France and the US were to fail. But the AI isn't yet clever enough to let the robotic forklift navigate on its own through an unfamiliar warehouse or take on a new task.

Note that the Buckeye Flats location (a) contains greater acoustic activity, a result of the nearby rapid flowing stream that produced considerable geophonic sounds. The inset (b) graphs the same data but with Buckeye Flats removed. These values (b) reflect mostly biophony. Sycamore Creek contained the greatest acoustic activity of these three. The fall contains the greatest activity although there was no consistent pattern across sites. Photos of each landscape are provided in (c).

Vivoka, a Lorraine-based company and French leader in speech recognition with the Voice Development Kit, announced in early January its participation in the partnership program of NXP Semiconductors, the world's tenth largest supplier of embedded controllers. The addition of NXP's technology to Vivoka's voice recognition artificial intelligence solution will benefit customers of both brands. Vivoka, a French company located in Metz, founded in 2015 by William Simonin, develops a solution that allows any company to add a voice interface to its products, very simply. This solution, called VDK (Voice Development Kit), is suitable for kiosks, robots, mobile applications, headsets… and has allowed it to become the French leader in voice recognition. Vivoka won the coveted Innovation Award in the sustainability and eco-design category at CES 2019.

Many astrophysical analyses depend on estimates of redshifts (a proxy for distance) determined from photometric (i.e., imaging) data alone. Inaccurate estimates of photometric redshift uncertainties can result in large systematic errors. However, probability distribution outputs from many photometric redshift methods do not follow the frequentist definition of a Probability Density Function (PDF) for redshift -- i.e., the fraction of times the true redshift falls between two limits $z_{1}$ and $z_{2}$ should be equal to the integral of the PDF between these limits. Previous works have used the global distribution of Probability Integral Transform (PIT) values to re-calibrate PDFs, but offsetting inaccuracies in different regions of feature space can conspire to limit the efficacy of the method. We leverage a recently developed regression technique that characterizes the local PIT distribution at any location in feature space to perform a local re-calibration of photometric redshift PDFs. Though we focus on an example from astrophysics, our method can produce PDFs which are calibrated at all locations in feature space for any use case.