Secretary of War Pete Hegseth highlighted the nation's "Drone Dominance" push for mass U.S. military drone adoption, noting plans to deliver tens of thousands in 2026.

House Speaker Mike Johnson, R-La., defends congressional investigations into the deadly Caribbean strike while comparing it to Obama-era drone operations.

President Biden delivers his farewell address to the nation from the White House. President Biden warned in his farewell speech of an "ultra-wealthy" "oligarchy" posing a threat to America as big tech CEOs have been warming up to President-elect Trump in recent months -- despite his own administration accepting donations from Democratic mega-donors. Biden spoke Wednesday as reports emerged this week that Elon Musk, Jeff Bezos and Mark Zuckerberg – the three most wealthy people in the world who collectively are worth more than 850 billion, according to Forbes – will be seated next to Trump's Cabinet picks and elected officials next Monday at his inauguration. "I have no doubt that America is in a position to continue to succeed. That's why in my farewell address tonight, I want to warn the country of some things that give me great concern. And the dangerous consequences if their abuse of power is left unchecked," Biden said from the Oval Office.

President Biden delivers his farewell address to the nation from the White House. President Biden warned in his farewell speech of an "ultra-wealthy" "oligarchy" posing a threat to America as big tech CEOS have been warming up to President-elect Trump in recent months. Biden spoke Wednesday as reports emerged this week that Elon Musk, Jeff Bezos and Mark Zuckerberg – the three most wealthy people in the world who collectively are worth more than 850 billion, according to Forbes – will be seated next to Trump's cabinet picks and elected officials next Monday at his inauguration. "I have no doubt that America is in a position to continue to succeed. That's why in my farewell address tonight, I want to warn the country of some things that give me great concern. And the dangerous consequences if their abuse of power is left unchecked," Biden said from the Oval Office.

"Your face is your ticket," goes the motto of A.I. startup Wicket. "Your face is your credential," says Alcatraz AI, another vendor. Both these companies sell facial recognition technology to sports stadiums across the country. Citi Field, home of the Mets, contracted with Wicket in 2022 to add facial recognition ticket kiosks to all stadium gates. BMO Stadium, home of the Los Angeles Football Club, began using Alcatraz AI technology the year before.

Lexical inference (LI) denotes the task of deciding Recently, transfer learning has become ubiquitous whether or not an entailment relation holds between in NLP; Transformer (Vaswani et al., two lexical items. It is therefore related to the detection 2017) language models (LMs) pretrained on large of other lexical relations like hyponymy amounts of textual data (Devlin et al., 2019a; Liu between nouns (Hearst, 1992), e.g., dog animal, et al., 2019) form the basis of a lot of current stateof-the-art or troponymy between verbs (Fellbaum and Miller, models. Besides zero-and few-shot capabilities 1990), e.g., to traipse to walk. Lexical inference (Radford et al., 2019; Brown et al., 2020), in context (LIiC) adds the problem of disambiguating pretrained LMs have also been found to acquire the pair of lexical items in a given context before factual and relational knowledge during pretraining reasoning about the inference question.

ENCODING GEOMETRIC INVARIANCES IN HIGHER-ORDER NEURAL NETWORKS C.L. Giles Air Force Office of Scientific Research, Bolling AFB, DC 20332 R.D. Griffin Naval Research Laboratory, Washington, DC 20375-5000 T. Maxwell Sachs-Freeman Associates, Landover, MD 20785 ABSTRACT We describe a method of constructing higher-order neural networks that respond invariantly under geometric transformations on the input space. By requiring each unit to satisfy a set of constraints on the interconnection weights, a particular structure is imposed on the network. A network built using such an architecture maintains its invariant performance independent of the values the weights assume, of the learning rules used, and of the form of the nonlinearities in the network. The invariance exhibited by a firstorder network is usually of a trivial sort, e.g., responding only to the average input in the case of translation invariance, whereas higher-order networks can perform useful functions and still exhibit the invariance. We derive the weight constraints for translation, rotation, scale, and several combinations of these transformations, and report results of simulation studies.

ENCODING GEOMETRIC INVARIANCES IN HIGHER-ORDER NEURAL NETWORKS C.L. Giles Air Force Office of Scientific Research, Bolling AFB, DC 20332 R.D. Griffin Naval Research Laboratory, Washington, DC 20375-5000 T. Maxwell Sachs-Freeman Associates, Landover, MD 20785 ABSTRACT We describe a method of constructing higher-order neural networks that respond invariantly under geometric transformations on the input space. By requiring each unit to satisfy a set of constraints on the interconnection weights, a particular structure is imposed on the network. A network built using such an architecture maintains its invariant performance independent of the values the weights assume, of the learning rules used, and of the form of the nonlinearities in the network. The invariance exhibited by a firstorder network is usually of a trivial sort, e.g., responding only to the average input in the case of translation invariance, whereas higher-order networks can perform useful functions and still exhibit the invariance. We derive the weight constraints for translation, rotation, scale, and several combinations of these transformations, and report results of simulation studies.

By requiring each unit to satisfy a set of constraints on the interconnection weights, a particular structure is imposed on the network. A network built using such an architecture maintains its invariant performance independent of the values the weights assume, of the learning rules used, and of the form of the nonlinearities in the network. The invariance exhibited by a firstorder networkis usually of a trivial sort, e.g., responding only to the average input in the case of translation invariance, whereas higher-order networks can perform useful functions and still exhibit the invariance. We derive the weight constraints for translation, rotation, scale, and several combinations of these transformations, and report results of simulation studies. INTRODUCTION A persistent difficulty for pattern recognition systems is the requirement that patterns or objects be recognized independent of irrelevant parameters or distortions such as orientation (position, rotation, aspect), scale or size, background or context, doppler shift, time of occurrence, or signal duration.