We propose an intuitive, machine-learning approach to multiparameter inference, dubbed the InferoStatic Networks (ISN) method, to model the score and likelihood ratio estimators in cases when the probability density can be sampled but not computed directly. The ISN uses a backend neural network that models a scalar function called the inferostatic potential $\varphi$. In addition, we introduce new strategies, respectively called Kernel Score Estimation (KSE) and Kernel Likelihood Ratio Estimation (KLRE), to learn the score and the likelihood ratio functions from simulated data. We illustrate the new techniques with some toy examples and compare to existing approaches in the literature. We mention en passant some new loss functions that optimally incorporate latent information from simulations into the training procedure.

Anomalies in univariate time series often refer to abnormal values and deviations from the temporal patterns from majority of historical observations. In multivariate time series, anomalies also refer to abnormal changes in the inter-series relationship, such as correlation, over time. Existing studies have been able to model such inter-series relationships through graph neural networks. However, most works settle on learning a static graph globally or within a context window to assist a time series forecasting task or a reconstruction task, whose objective is not tailored to explicitly detect the abnormal relationship. Some other works detect anomalies based on reconstructing or forecasting a list of inter-series graphs, which inadvertently weakens their power to capture temporal patterns within the data due to the discrete nature of graphs. In this study, we propose DyGraphAD, a multivariate time series anomaly detection framework based upon a list of dynamic inter-series graphs. The core idea is to detect anomalies based on the deviation of inter-series relationships and intra-series temporal patterns from normal to anomalous states, by leveraging the evolving nature of the graphs in order to assist a graph forecasting task and a time series forecasting task simultaneously. Our numerical experiments on real-world datasets demonstrate that DyGraphAD has superior performance than baseline anomaly detection approaches.

Sentiment Analysis Systems (SASs) are data-driven Artificial Intelligence (AI) systems that, given a piece of text, assign one or more numbers conveying the polarity and emotional intensity expressed in the input. Like other automatic machine learning systems, they have also been known to exhibit model uncertainty where a (small) change in the input leads to drastic swings in the output. This can be especially problematic when inputs are related to protected features like gender or race since such behavior can be perceived as a lack of fairness, i.e., bias. We introduce a novel method to assess and rate SASs where inputs are perturbed in a controlled causal setting to test if the output sentiment is sensitive to protected variables even when other components of the textual input, e.g., chosen emotion words, are fixed. We then use the result to assign labels (ratings) at fine-grained and overall levels to convey the robustness of the SAS to input changes. The ratings serve as a principled basis to compare SASs and choose among them based on behavior. It benefits all users, especially developers who reuse off-the-shelf SASs to build larger AI systems but do not have access to their code or training data to compare.

We reconstruct the extra-galactic gamma-ray source-count distribution, or $dN/dS$, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the Fermi-LAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the $(1,10)$ GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from catalogued sources, and then extends as $dN/dS \sim S^{-2}$ in the unresolved regime, down to fluxes of $5 \cdot 10^{-12}$ cm$^{-2}$ s$^{-1}$. The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep reinforcement learning (DRL) framework to learn proactive, context-aware, defense countermeasures that dynamically adapt to evolving adversarial behaviors while minimizing loss of cyber system operations. A dynamic defense optimization problem is formulated with multiple protective postures against different types of adversaries with varying levels of skill and persistence. A custom simulation environment was developed and experiments were devised to systematically evaluate the performance of four model-free DRL algorithms against realistic, multi-stage attack sequences. Our results suggest the efficacy of DRL algorithms for proactive cyber defense under multi-stage attack profiles and system uncertainties.

A flexible topological representation consisting of a two-layer graph structure built on-board an Unmanned Aerial Vehicle (UAV) by continuously filling the free space of an occupancy map with intersecting spheres is proposed in this \paper{}. Most state-of-the-art planning methods find the shortest paths while keeping the UAV at a pre-defined distance from obstacles. Planning over the proposed structure reaches this pre-defined distance only when necessary, maintaining a safer distance otherwise, while also being orders of magnitude faster than other state-of-the-art methods. Furthermore, we demonstrate how this graph representation can be converted into a lightweight shareable topological-volumetric map of the environment, which enables decentralized multi-robot cooperation. The proposed approach was successfully validated in several kilometers of real subterranean environments, such as caves, devastated industrial buildings, and in the harsh and complex setting of the final event of the DARPA SubT Challenge, which aims to mimic the conditions of real search and rescue missions as closely as possible, and where our approach achieved the \nth{2} place in the virtual track.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Connecticut needs safeguards on state government's use of artificial intelligence including algorithms at child welfare and other agencies to prevent discrimination and increase transparency, an advisory panel to the U.S. Commission on Civil Rights said Thursday. The Connecticut Advisory Committee to the federal commission called on state lawmakers to pass laws regulating such systems, which have sparked concerns in other parts of the country. The problem, critics say, is algorithms can use flawed data that can disproportionately identify minorities, low-income families, disabled people and other groups when agencies make decisions on removing children from homes, approving health, housing and other benefits, where to concentrate law enforcement and assigning children to schools, among other uses.

Amazon's drone delivery program doesn't seem to be off to a great start. The Prime Air division was said to be hit hard by recent, widespread layoffs. Now, a new report indicates that Amazon's drones have made just a handful of deliveries in their first few weeks of operation. After nearly a decade of working on the program, Amazon said in December that it would start making deliveries by drone in Lockeford, California, and College Station, Texas. However, by the middle of January, as few as seven houses had received Amazon packages by drone, according to The Information: two in California and five in Texas.

WASHINGTON, Feb 1 (Reuters) - U.S. investors including the investment arms of Intel Corp (INTC.O) and Qualcomm Inc (QCOM.O) accounted for nearly a fifth of investments in Chinese artificial intelligence companies from 2015 to 2021, a report showed on Wednesday. The document, released by CSET, a tech policy group at Georgetown University, comes amid growing scrutiny of U.S. investments in AI, Quantum and semiconductors, as the Biden administration prepares to unveil new restrictions on U.S. funding of Chinese tech companies. According to the report, 167 U.S. investors took part in 401 transactions, or roughly 17% of the investments into Chinese AI companies in the period. Those transactions represented a total $40.2 billion in investment, or 37% of the total raised by Chinese AI companies in the 6-year period. It was not clear from the report, which pulled information from data provider Crunchbase, what percentage of the funding came from the U.S. firms.

House Oversight Committee Chairman James Comer told reporters Tuesday he believes Hunter Biden was "in proximity" to the classified documents found in President Biden's garage. Hunter Biden's lawyers called on federal and state prosecutors across the country to open criminal investigations into his critics on Wednesday – and in doing so, acknowledged that the notorious laptop is indeed Hunter's. Biden's attorney, Abbe Lowell, wrote letters to the Justice Department and the Delaware attorney general calling for investigations into Rudy Giuliani, Steve Bannon and John Mac Isaac, who owns the computer repair shop where Biden is said to have left his laptop. Biden's lawyers also sent cease and desist letters to others who obtained and disseminated the laptop's contents. Lowell argued in the letters that Mac Isaac and the others had no right to inspect the contents of Biden's laptop, much less make copies of it to share with the media.