Beyond local convolution networks, we explore how to harness various external human knowledge for endowing the networks with the capability of semantic global reasoning.

We propose a new type of generative model for high-dimensional data that learns a manifold geometry of the data, rather than density, and can generate points evenly along this manifold. This is in contrast to existing generative models that represent data density, and are strongly affected by noise and other artifacts of data collection. We demonstrate how this approach corrects sampling biases and artifacts, thus improves several downstream data analysis tasks, such as clustering and classification. Finally, we demonstrate that this approach is especially useful in biology where, despite the advent of single-cell technologies, rare subpopulations and gene-interaction relationships are affected by biased sampling. We show that SUGAR can generate hypothetical populations, and it is able to reveal intrinsic patterns and mutual-information relationships between genes on a single-cell RNA sequencing dataset of hematopoiesis.

We consider a multi-armed bandit game where N players compete for K arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed. Performance is measured using the expected sum of regrets, compared to the optimal assignment of arms to players. We assume that each player only knows her actions and the reward she received each turn. Players cannot observe the actions of other players, and no communication between players is possible. We present a distributed algorithm and prove that it achieves an expected sum of regrets of near-O\left(\log^{2}T\right). This is the first algorithm to achieve a poly-logarithmic regret in this fully distributed scenario. All other works have assumed that either all players have the same vector of expected rewards or that communication between players is possible.

Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have remained poor, at least in comparison with ANNs. We address two possible reasons for that. One is that RSNNs in the brain are not randomly connected or designed according to simple rules, and they do not start learning as a tabula rasa network. Rather, RSNNs in the brain were optimized for their tasks through evolution, development, and prior experience. Details of these optimization processes are largely unknown. But their functional contribution can be approximated through powerful optimization methods, such as backpropagation through time (BPTT). A second major mismatch between RSNNs in the brain and models is that the latter only show a small fraction of the dynamics of neurons and synapses in the brain. We include neurons in our RSNN model that reproduce one prominent dynamical process of biological neurons that takes place at the behaviourally relevant time scale of seconds: neuronal adaptation.

Subhalata Pradhan, a Gram Vikas fieldworker, talks to Raja Pradhan about the chatbot and addresses concerns over sharing his details. Subhalata Pradhan, a Gram Vikas fieldworker, talks to Raja Pradhan about the chatbot and addresses concerns over sharing his details. India's scattered workforce: the chatbot keeping families in touch during emergencies Covid exposed the lack of data on the country's 140 million mobile migrant workers, but a new project in Odisha is helping to fill in the gaps Mon 16 Mar 2026 02.00 EDTLast modified on Mon 16 Mar 2026 02.03 EDT Raja Pradhan is sitting cross-legged, scrolling on his phone in his village in eastern India when a green WhatsApp chat bubble pops up on the screen. Are you going outside for work? He reads the message twice, unsure whether to respond.

Has Trump failed to sell the Iran war to the world? Are US-Israeli attacks against Iran legal? As anticipated, it ended up being One Battle After Another's night at the 98th annual Academy Awards, with the political thriller carting away six Oscars out of a total of 13 nominations. But while Paul Thomas Anderson's magnum opus continued its march towards awards-season domination, there were moments of genuine surprise and subversion in Sunday's ceremony. Host Conan O'Brien and his fellow presenters deftly avoided mentioning President Donald Trump by name, but their barbs took direct aim at his policies since returning to office.

Gaussian processes provide a flexible framework for forecasting, removing noise, and interpreting long temporal datasets. State space modelling (Kalman filtering) enables these non-parametric models to be deployed on long datasets by reducing the complexity to linear in the number of data points. The complexity is still cubic in the state dimension m which is an impediment to practical application. In certain special cases (Gaussian likelihood, regular spacing) the GP posterior will reach a steady posterior state when the data are very long. We leverage this and formulate an inference scheme for GPs with general likelihoods, where inference is based on single-sweep EP (assumed density filtering). The infinite-horizon model tackles the cubic cost in the state dimensionality and reduces the cost in the state dimension m to O(m^2) per data point. The model is extended to online-learning of hyperparameters. We show examples for large finite-length modelling problems, and present how the method runs in real-time on a smartphone on a continuous data stream updated at 100 Hz.

Oscars 2026: Here are all the moments you didn't see on TV The 98th Academy Awards featured emotional speeches, comical relief and a bevy of backstage fun. While movie magic plays a role in the show itself (the ceremony, after all, is actually hosted at the Dolby Theatre in a shopping centre), there is a lot you don't see on TV. Frankenstein production designer addressed the media with his Oscar statuette in one hand and what appeared to be a beer in the other and Mr Nobody Against Putin filmmaker Pasha Talankin re-lived his Oscars win by re-reading the envelope that announced that his movie won the award for documentary feature film. We saw some of the tightest security in recent years and witnessed the frenzied panic after one Oscar award became two when those vying for best short action film was announced as a historic tie. Here's what it's like on the scene during Hollywood's biggest night and everything you did not see on TV.

U.S. President Donald Trump speaks to reporters aboard Air Force One on a flight to Washington on Sunday. SAN FRANCISCO - U.S. President Donald Trump on Sunday accused Iran of using artificial intelligence as a "disinformation weapon" to misrepresent its wartime successes and support. "AI can be very dangerous, we have to be very careful with it," Trump said to reporters on Air Force One shortly after he made a post on his Truth Social platform where he accused Western media outlets without evidence of "close coordination" with Iran to spread AI-generated fake news." The comments come amid renewed tensions between the Federal Communications Commission and broadcasters after Trump took aim at media coverage of the U.S. and Israel's war with Iran. FCC Chairman Brendan Carr on Saturday threatened to pull licenses of broadcasters who did not "correct course" on their coverage.

Prior work has investigated variations of prediction markets that preserve participants' (differential) privacy, which formed the basis of useful mechanisms for purchasing data for machine learning objectives. Such markets required potentially unlimited financial subsidy, however, making them impractical. In this work, we design an adaptively-growing prediction market with a bounded financial subsidy, while achieving privacy, incentives to produce accurate predictions, and precision in the sense that market prices are not heavily impacted by the added privacy-preserving noise. We briefly discuss how our mechanism can extend to the data-purchasing setting, and its relationship to traditional learning algorithms.