The FDA has approved an artificial intelligence-based test for early detection of dementia that can be carried out on an iPad in five minutes. The CognICA Integrated Cognitive Assessment (ICA) test developed by London, UK-based company Cognetivity Neurosciences has been approved by the FDA as an alternative to traditional pen-and-paper tests with some key advantages, according to its developer. Those include high sensitivity to detect early-stage cognitive impairment, which could allow early intervention with treatment or lifestyle changes that might help to slow down the progression of dementia. The digital format also helps to avoid cultural or educational bias in testing, and helps to avoid scenarios where people tested on multiple occasions learn how to score better, masking increases in impairment, said Cognetivity. It can also be carried out unsupervised, saving time and money for health systems and making it particularly suitable for assessments when access to care may be restricted, or to allow ongoing monitoring of patients without clinic visits.

Artificial Intelligence (AI) is the simulation of human intelligence in computers, and they are trained to think and act in the same way as humans do. It can also refer to any computer that demonstrates human-like characteristics such as problem-solving and learning. The ability of Artificial Intelligence to reason and act and achieve a specific goal is the ideal trait. Machine learning is a subset of Artificial Intelligence that relates to the concept of computer systems learning and adapting to new data without the need for human intervention. Deep learning algorithms enable this self-learning by absorbing large amounts of unstructured data such as text, images, and video.

Artificial intelligence and machine learning systems may help 5G cloud providers detect the presence of sophisticated attackers and other security incidents, according to new guidance from the National Security Agency. In a report published on Thursday, the intelligence agency said that while technology providers would have to balance data confidentiality requirements with the ability to inspect network traffic, sophisticated real-time continuous monitoring may be crucial in detecting the malicious use of cloud resources. "Stakeholders at all layers of the 5G cloud stack should leverage an analytic platform to develop and deploy analytics that process relevant data (cloud logs and other telemetry) available at that layer. The analytics should be capable of detecting known and anticipated threat, but also be designed to identify anomalies in the data that could indicate unanticipated threat," the agency said in the document. The NSA detailed the potential use of AI monitoring systems in the first part of a new four-part report series it is publishing to provide guidance for 5G network stakeholders, including service providers and systems integrators.

Air Force fighter pilots will soon face new opponents in their training: artificial intelligence-based enemy pilots that can match humans based on their personal learning needs. After steering the production of numerous AI-enabled pilot agents for years, Aptima, Inc. confirmed it landed a four-year contract with the Air Force Research Laboratory to build an "automated librarian" that will categorize those AI pilots and pair them with military trainees in scenarios that are right to advance their skillsets. "The best case outcome is that AFRL determines that the products of this research are so promising that they create a library into which AI training technologies are shelved like books are shelved and they refine the sort of librarian that we're trying to build here so that it can sweep through that enormous library of AI, sweep through a library of scenarios--and for each individual student--pick out just the right pairing to advance them to expertise reliably and more quickly than we can do today," Aptima's Chief Scientist Jared Freeman told Nextgov during an interview on Tuesday. Freeman joined the company in 1999, four years after its launch. Aptima's project portfolio has grown increasingly diverse since then, he noted. Now, much of it concerns AI support for human teams, like forming and measuring them, and helping people and AI to manage those groups.

Fast and accurate prediction of hurricane evolution from genesis onwards is needed to reduce loss of life and enhance community resilience. In this work, a novel model development methodology for predicting storm trajectory is proposed based on two classes of Recurrent Neural Networks (RNNs). The RNN models are trained on input features available in or derived from the HURDAT2 North Atlantic hurricane database maintained by the National Hurricane Center (NHC). The models use probabilities of storms passing through any location, computed from historical data. A detailed analysis of model forecasting error shows that Many-To-One prediction models are less accurate than Many-To-Many models owing to compounded error accumulation, with the exception of $6-hr$ predictions, for which the two types of model perform comparably. Application to 75 or more test storms in the North Atlantic basin showed that, for short-term forecasting up to 12 hours, the Many-to-Many RNN storm trajectory prediction models presented herein are significantly faster than ensemble models used by the NHC, while leading to errors of comparable magnitude.

In this paper, we use and further develop upon a recently proposed multivariate, distribution-free Goodness-of-Fit (GoF) test based on the theory of Optimal Transport (OT) called the Rank Energy (RE) [1], for non-parametric and unsupervised Change Point Detection (CPD) in multivariate time series data. We show that directly using RE leads to high sensitivity to very small changes in distributions (causing high false alarms) and it requires large sample complexity and huge computational cost. To alleviate these drawbacks, we propose a new GoF test statistic called as soft-Rank Energy (sRE) that is based on entropy regularized OT and employ it towards CPD. We discuss the advantages of using sRE over RE and demonstrate that the proposed sRE based CPD outperforms all the existing methods in terms of Area Under the Curve (AUC) and F1-score on real and synthetic data sets.

We consider the problem of generating valid knockoffs for knockoff filtering which is a statistical method that provides provable false discovery rate guarantees for any model selection procedure. To this end, we are motivated by recent advances in multivariate distribution-free goodness-of-fit tests namely, the rank energy (RE), that is derived using theoretical results characterizing the optimal maps in the Monge's Optimal Transport (OT) problem. However, direct use of use RE for learning generative models is not feasible because of its high computational and sample complexity, saturation under large support discrepancy between distributions, and non-differentiability in generative parameters. To alleviate these, we begin by proposing a variant of the RE, dubbed as soft rank energy (sRE), and its kernel variant called as soft rank maximum mean discrepancy (sRMMD) using entropic regularization of Monge's OT problem. We then use sRMMD to generate deep knockoffs and show via extensive evaluation that it is a novel and effective method to produce valid knockoffs, achieving comparable, or in some cases improved tradeoffs between detection power Vs false discoveries.

Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism. On the other hand, although kernel machines suffer from the same computation bottleneck in pairwise dot products, several approximation schemes have been successfully incorporated to considerably reduce their computational cost without sacrificing too much accuracy. In this work, we leverage the computation methods for kernel machines to alleviate the high computational cost and introduce Skyformer, which replaces the softmax structure with a Gaussian kernel to stabilize the model training and adapts the Nystr\"om method to a non-positive semidefinite matrix to accelerate the computation. We further conduct theoretical analysis by showing that the matrix approximation error of our proposed method is small in the spectral norm. Experiments on Long Range Arena benchmark show that the proposed method is sufficient in getting comparable or even better performance than the full self-attention while requiring fewer computation resources.

Given Spatial Variability Aware Neural Networks (SVANNs), the goal is to investigate mathematical (or computational) models for comparative physical interpretation towards their transparency (e.g., simulatibility, decomposability and algorithmic transparency). This problem is important due to important use-cases such as reusability, debugging, and explainability to a jury in a court of law. Challenges include a large number of model parameters, vacuous bounds on generalization performance of neural networks, risk of overfitting, sensitivity to noise, etc., which all detract from the ability to interpret the models. Related work on either model-specific or model-agnostic post-hoc interpretation is limited due to a lack of consideration of physical constraints (e.g., mass balance) and properties (e.g., second law of geography). This work investigates physical interpretation of SVANNs using novel comparative approaches based on geographically heterogeneous features. The proposed approach on feature-based physical interpretation is evaluated using a case-study on wetland mapping. The proposed physical interpretation improves the transparency of SVANN models and the analytical results highlight the trade-off between model transparency and model performance (e.g., F1-score). We also describe an interpretation based on geographically heterogeneous processes modeled as partial differential equations (PDEs).

What does it mean to be first in developing applications of artificial intelligence (AI), and does it matter? In a recent interview, the former Chief Software Officer of the U.S. Air Force Nicolas Chaillan stated that he resigned in part because he believed that, "We have no competing chance against China in fifteen to twenty years. Right now, it's already a done deal; it is already over." He reasoned that a failure of the U.S. Department of Defense (DoD) to follow through on stated intentions to build up in AI and cyber means many departments within DoD still operate at what Chaillan considers a "kindergarten level." Those are strong words, but Chaillan's overall assessment misses the mark--the United States becoming an AI also-ran is not a foregone conclusion.