Neural Information Processing Systems http://nips.cc/

This study introduces a novel feature selection approach CMICOT, which is a further evolution of filter methods with sequential forward selection (SFS) whose scoring functions are based on conditional mutual information (MI). We state and study a novel saddle point (max-min) optimization problem to build a scoring function that is able to identify joint interactions between several features. This method fills the gap of MI-based SFS techniques with high-order dependencies. In this high-dimensional case, the estimation of MI has prohibitively high sample complexity. We mitigate this cost using a greedy approximation and binary representatives what makes our technique able to be effectively used. The superiority of our approach is demonstrated by comparison with recently proposed interactionaware filters and several interaction-agnostic state-of-the-art ones on ten publicly available benchmark datasets.

In the past, voice assistants like Siri or the one in your satnav used so-called'synthetic voices'. These require voice actors to spend hours in the recording studio, meticulously sampling all the different words and phrases that the assistant might need. Voice clones, on the other hand, have revolutionised how synthetic voices are created, by using AI to digitally recreate someone's speech patterns. These clones can be created with as little as a few seconds of recorded audio, even using clips from social media or snippets of conversation as the raw material. This has sparked concerns that criminals using AI could easily impersonate friends, family, or co-workers to manipulate their targets . According to the National Trading Standards, criminals are already using AI to clone people's voices and set up unauthorised direct debits over the phone. In the study, the researchers created voice clones of human participants using just 120 pre-recorded sentences. Participants listened to 80 unique sentences - 40 spoken by a real person and 40 spoken by an AI voice clone. The researchers compared human (top) AI-generated (bottom) voice recordings to see why this might be the case, but couldn't find any clear explanation Can you tell which voices are AI?

The elite Wall Street law firm Sullivan & Cromwell has told a court that a major filing it made in a high-profile case contained errors resulting from hallucinations generated by artificial intelligence. Andrew Dietderich, the co-head of the firm's global restructuring group, apologised in a letter to the New York federal judge Martin Glenn on Saturday for the string of mistakes, which included inaccurate citations. The errors, uncovered by the law firm Boies Schiller Flexner (BSF), which was also working on the case, included misquoting the US bankruptcy code and citing cases incorrectly in a filing made on 9 April. In multiple instances, S&C, which employs more than 900 lawyers and has one of the top reputations for corporate work in the US, filed inaccurately summarised conclusions made in other cases using AI. "We deeply regret that this has occurred," said Dietderich in the letter.

Terra Drone's Terra A1 interceptor drone has entered active combat use in Ukraine after being deployed to a military unit tasked with countering Russian uncrewed aerial systems. Japanese drone company Terra Drone said its Terra A1 interceptor -- developed with its Ukrainian partner Amazing Drones -- has moved from the lab to the front lines, entering active combat use in Ukraine against Russian-made Shahed drones. "Deployment for defense purposes has already begun with a military unit, and evaluation and feedback collection under actual operating conditions are currently under way," the Tokyo-based firm, which recently made a strategic investment in the Ukrainian startup, said in a recent statement. Terra Drone explained that this initial "real-world operational deployment" -- carried out via its local partner -- will follow a phased rollout, where new equipment is first issued to a single unit and then expanded to further deployments depending on evaluations from the field. In a time of both misinformation and too much information, quality journalism is more crucial than ever.

The restricted isometry property (RIP) for design matrices gives guarantees for optimal recovery in sparse linear models. It is of high interest in compressed sensing and statistical learning. This property is particularly important for computationally efficient recovery methods. As a consequence, even though it is in general NP-hard to check that RIP holds, there have been substantial efforts to find tractable proxies for it. These would allow the construction of RIP matrices and the polynomial-time verification of RIP given an arbitrary matrix. We consider the framework of average-case certifiers, that never wrongly declare that a matrix is RIP, while being often correct for random instances. While there are such functions which are tractable in a suboptimal parameter regime, we show that this is a computationally hard task in any better regime. Our results are based on a new, weaker assumption on the problem of detecting dense subgraphs.

We demonstrate how quantum computation can provide non-trivial improvements in the computational and statistical complexity of the perceptron model. We develop two quantum algorithms for perceptron learning. The first algorithm exploits quantum information processing to determine a separating hyperplane using a number of steps sublinear in the number of data points N, namely O( N). The second algorithm illustrates how the classical mistake bound of O( 1γ2) can be further improved to O( 1 γ) through quantum means, where γ denotes the margin. Such improvements are achieved through the application of quantum amplitude amplification to the version space interpretation of the perceptron model.

We study the problem of completing a binary matrix in an online learning setting. On each trial we predict a matrix entry and then receive the true entry. We propose a Matrix Exponentiated Gradient algorithm [1] to solve this problem. We provide a mistake bound for the algorithm, which scales with the margin complexity [2, 3] of the underlying matrix. The bound suggests an interpretation where each row of the matrix is a prediction task over a finite set of objects, the columns. Using this we show that the algorithm makes a number of mistakes which is comparable up to a logarithmic factor to the number of mistakes made by the Kernel Perceptron with an optimal kernel in hindsight. We discuss applications of the algorithm to predicting as well as the best biclustering and to the problem of predicting the labeling of a graph without knowing the graph in advance.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/