Meta wants you to understand anyone, from anywhere, no matter which language they speak. To achieve this the company is looking to build a universal, instantaneous speech translator, capable of translating any language to any other language -- including languages that are primarily spoken. Mark Zuckerberg announced this goal during an AI-focused event Wednesday, describing it as a key step toward a world-encompassing metaverse. "The ability to communicate with anyone in any language -- that's a superpower people have dreamed of forever, and AI is going to deliver that in our lifetimes." Meta's ambitious universal translation project is part of a broader push to build out the company's translation capabilities for the metaverse.

Last year, researchers at Data Science Nigeria noted that engineers looking to train computer-vision algorithms could choose from a wealth of data sets featuring Western clothing, but there were none for African clothing. The team addressed the imbalance by using AI to generate artificial images of African fashion--a whole new data set from scratch. Such synthetic data sets--computer-generated samples with the same statistical characteristics as the genuine article--are growing more and more common in the data-hungry world of machine learning. These fakes can be used to train AIs in areas where real data is scarce or too sensitive to use, as in the case of medical records or personal financial data. The idea of synthetic data isn't new: driverless cars have been trained on virtual streets.

The adaptive processing of structured data is a long-standing research topic in machine learning that investigates how to automatically learn a mapping from a structured input to outputs of various nature. Recently, there has been an increasing interest in the adaptive processing of graphs, which led to the development of different neural network-based methodologies. In this thesis, we take a different route and develop a Bayesian Deep Learning framework for graph learning. The dissertation begins with a review of the principles over which most of the methods in the field are built, followed by a study on graph classification reproducibility issues. We then proceed to bridge the basic ideas of deep learning for graphs with the Bayesian world, by building our deep architectures in an incremental fashion. This framework allows us to consider graphs with discrete and continuous edge features, producing unsupervised embeddings rich enough to reach the state of the art on several classification tasks. Our approach is also amenable to a Bayesian nonparametric extension that automatizes the choice of almost all model's hyper-parameters. Two real-world applications demonstrate the efficacy of deep learning for graphs. The first concerns the prediction of information-theoretic quantities for molecular simulations with supervised neural models. After that, we exploit our Bayesian models to solve a malware-classification task while being robust to intra-procedural code obfuscation techniques. We conclude the dissertation with an attempt to blend the best of the neural and Bayesian worlds together. The resulting hybrid model is able to predict multimodal distributions conditioned on input graphs, with the consequent ability to model stochasticity and uncertainty better than most works. Overall, we aim to provide a Bayesian perspective into the articulated research field of deep learning for graphs.

The bizarre promotional video promises "Face analysis based on best of breed Artificial Intelligence algorithms for Business Intelligence and Digital Signage applications." What follows is footage of a woman pushing her hair behind her ears, a man grimacing and baring his teeth, and an actor in a pinstripe suit being slapped in the face against a green screen. Digitally overlayed on each person's face are colored outlines of rectangles with supposed measurements displayed: "F 25 happiness," "caucasian_latin," "M 38 sadness." The commercial reel advertises just one of the many video analytics tools available for download on an app store monitored by the Internet of Things startup Azena, itself a project from the German kitchen appliance maker Bosch. Bosch, known more for its line of refrigerators, ovens, and dishwashers, also develops and sells an entire suite of surveillance cameras.

Most of us have a music, movie or video-game library – possibly all three – but few have an art collection or even know what their favourite works of art are. Next year, that will change as art moves from the inaccessible to the everyday, thanks to AI. Art hasn't felt accessible to many for a long time. Our main experience of it involves visiting galleries and museums or feeling out our depth in art history classes. At a gallery, we spend a couple of hours looking at a lot of seemingly important pieces, but then we leave and the artworks stay where they are. They don't draw us in, like a favourite album, movie or video game, and we know we can't afford to take them home with us.

The United States has issued fresh sanctions on alleged members of an illicit network financing Yemen's Houthi rebels, citing the group's involvement in the continuing war in Yemen and recent drone and missile attacks on Washington's Gulf allies. In a statement on Wednesday, the US Department of the Treasury said the network "has transferred tens of millions of dollars to Yemen via a complex international network of intermediaries in support of the Houthis' attacks". The new sanctions target alleged front companies and ships that the US says worked with a branch of Iran's Islamic Revolutionary Guard Corps to smuggle petroleum and other commodities around the Middle East, Asia and Africa to help fund the Houthis. "Despite pleas to negotiate an end to this devastating conflict, Houthi leaders continue to launch missile and unmanned aerial vehicle attacks against Yemen's neighbors, killing innocent civilians, while millions of Yemeni civilians remain displaced and hungry," Treasury Under-secretary Brian E Nelson said in the statement. The Houthi rebels have ramped up their missile and drone attacks against Saudi Arabia and started directly targeting the UAE in recent weeks, but the penalties appeared to fall short of the tougher measures that the Saudis and Emiratis, key strategic partners of the US, had sought from the Biden administration.

During an Inside the Lab: Building for the metaverse with AI livestream event on Wednesday, Meta CEO Mark Zuckerberg didn't just expound on his company's unblinking vision for the future, dubbed the Metaverse. He also revealed that Meta's research division is working on a universal speech translation system that could streamline users' interactions with AI within the company's digital universe. "The big goal here is to build a universal model that can incorporate knowledge across all modalities... all the information that is captured through rich sensors," Zuckerberg said. "This will enable a vast scale of predictions, decisions, and generation as well as whole new architectures training methods and algorithms that can learn from a vast and diverse range of different inputs." Zuckerberg noted that Facebook has continually striven to develop technologies that enable more people worldwide to access the internet and is confident that those efforts will translate to the Metaverse as well.

This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching with independent edge weights to geometric models. Specifically, given a random permutation $\pi^*$ on $[n]$ and $n$ iid pairs of correlated Gaussian vectors $\{X_{\pi^*(i)}, Y_i\}$ in $\mathbb{R}^d$ with noise parameter $\sigma$, the edge weights are given by $A_{ij}=\kappa(X_i,X_j)$ and $B_{ij}=\kappa(Y_i,Y_j)$ for some link function $\kappa$. The goal is to recover the hidden vertex correspondence $\pi^*$ based on the observation of $A$ and $B$. We focus on the dot-product model with $\kappa(x,y)=\langle x, y \rangle$ and Euclidean distance model with $\kappa(x,y)=\|x-y\|^2$, in the low-dimensional regime of $d=o(\log n)$ wherein the underlying geometric structures are most evident. We derive an approximate maximum likelihood estimator, which provably achieves, with high probability, perfect recovery of $\pi^*$ when $\sigma=o(n^{-2/d})$ and almost perfect recovery with a vanishing fraction of errors when $\sigma=o(n^{-1/d})$. Furthermore, these conditions are shown to be information-theoretically optimal even when the latent coordinates $\{X_i\}$ and $\{Y_i\}$ are observed, complementing the recent results of [DCK19] and [KNW22] in geometric models of the planted bipartite matching problem. As a side discovery, we show that the celebrated spectral algorithm of [Ume88] emerges as a further approximation to the maximum likelihood in the geometric model.

Artificial Intelligence (AI), is a societal buzzword that now crosses every area of human experience. Whether it is our leisure activities, our medical interventions, our banking transactions or our shopping pursuits, AI is now pivotal to the way in which we conduct our personal lives. This phenomenon has not emerged haphazardly, but is a trajectory that has ensued from the benefits that business has enjoyed from its use, and one that now every area of commerce needs to employ, and maintain, in order to enjoy any success. According to IBM, 65 percent of all organisations will have accelerated the use of digital technologies by 2022 and more than 85 percent of advanced adopters are reducing operating costs. Artificial Intelligence is here to stay.

The United States Navy announced the launch of a new joint fleet of unmanned drones in the Middle East with allied nations to patrol vast swaths of volatile waters as tensions simmer with Iran. Vice Admiral Brad Cooper, who leads the 5th Fleet, said 100 unmanned drones, both sailing and submersible, would dramatically multiply the surveillance capacities of the US Navy, allowing it to keep a close eye on waters critical to the flow of global oil and shipping. Trade at sea has been targeted in recent years as Tehran's nuclear deal with world powers collapsed. "By using unmanned systems, we can just simply see more. They're high reliability and remove the human factor," Cooper said on the sidelines of a defence exhibition in Abu Dhabi, adding the systems are "the only way to cover on whatever gaps that we have today".