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

This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the network. Mainly, we investigate how the Fiedler partition of the dual graph and show that it appears to correlate with the decision boundary -- in the case of binary classification. Additionally, we compute the homology of the cellular decomposition -- in a regression task -- to draw similar patterns in behavior between the training loss and polyhedral cell-count, as the model is trained.

In classical canonical correlation analysis (CCA), the goal is to determine the linear transformations of two random vectors into two new random variables that are most strongly correlated. Canonical variables are pairs of these new random variables, while canonical correlations are correlations between these pairs. In this paper, we propose and study two generalizations of this classical method: (1) Instead of two random vectors we study more complex data structures that appear in important applications. In these structures, there are $L$ features, each described by $p_l$ scalars, $1 \le l \le L$. We observe $n$ such objects over $T$ time points. We derive a suitable analog of the CCA for such data. Our approach relies on embeddings into Reproducing Kernel Hilbert Spaces, and covers several related data structures as well. (2) We develop an analogous approach for multidimensional random processes. In this case, the experimental units are multivariate continuous, square-integrable functions over a given interval. These functions are modeled as elements of a Hilbert space, so in this case, we define the multiple functional canonical correlation analysis, MFCCA. We justify our approaches by their application to two data sets and suitable large sample theory. We derive consistency rates for the related transformation and correlation estimators, and show that it is possible to relax two common assumptions on the compactness of the underlying cross-covariance operators and the independence of the data.

More'Frankenstein' rabbits are appearing across the US, sparking fears of a wider outbreak. Originally spotted in Colorado, these bizarre rabbits, with tentacle-like growths sprouting from their faces, have now been reported in Minnesota, Nebraska, and South Dakota. The animals are infected with cottontail rabbit papilloma virus (CRPV), also known as Shope papilloma virus, which can be spread through mosquito and tick bites. While humans are unlikely to contract CRPV, Dr Omer Awan of the University of Maryland School of Medicine cautioned that people could still face risks from other diseases carried by ticks or mosquitoes that have fed on infected rabbits. 'You're not going to get CRPV, and you likely won't show symptoms of it,' Dr Awan told the Daily Mail.

Once best known for developing the Taser, Axon has transformed into a 50 billion military and law enforcement tech giant.Mother Jones illustration; Michael Nigro/Pacific Press/Zuma; Arthur Ogleznev/Unsplash; Logan Weaver/Unsplash In April 2024, the American police tech firm Axon, which leads the market for police body cameras, released a tool it billed as "revolutionary": Draft One, an AI-powered software package that would turn body camera footage and audio into intelligible police reports. Once best known for developing the Taser, Axon has transformed into a 50 billion military and law enforcement tech giant, providing more than 5,000 police departments across the country with a suite of cloud-based products to manage evidence collection and storage. Draft One, the AI tool, connects with the company's body cameras and evidence storage service to write police reports with little human intervention. At least 21 departments have experimented with the software. The use of artificial intelligence in generating police reports has been particularly troubling, according to civil rights advocacy groups like the Electronic Frontier Foundation and ACLU, because of generative AI's propensity towards racial and gender bias, and its tendency to insert inaccuracies into texts--including wholesale inventions known by technologists as "hallucinations." "I can almost guarantee [AI] reports have been used in plea deals," a police captain wrote.

The bizarre virus turning harmless rabbits into terrifying, tentacle-faced creatures has been spotted by more Americans, sparking fears that a wildlife crisis is emerging. The'Frankenstein' rabbits recently made headlines in Colorado, as locals reported seeing the infected animals wandering through neighborhoods. However, the sightings have not been isolated that state. Residents in Minnesota and Nebraska have shared more images and stories of these deformed rabbits popping up. The rabbits are infected with the cottontail papilloma virus (CRPV), also known as Shope papilloma virus, which causes horn- or tentacle-like tumors to grow around the animals' heads and faces.

A mysterious virus has left ordinary rabbits in the US with shocking deformities, including faces full of horns and tentacles. The mutated rabbits have been spotted multiple times in Colorado, specifically in the city of Fort Collins. The sightings date back to 2024, when a Fort Collins resident shared a picture online, showing the creature's entire head covered in black, tentacle-like protrusions. It's believed the horns are due to a virus that causes cancerous growths and has no known cure. Colorado Parks and Wildlife (CPW) has urged anyone who sees rabbits in the wild with these growths to stay away and not touch them.

The High-Resolution Rapid Refresh (HRRR) model is a convection-allowing model used in operational weather forecasting across the contiguous United States (CONUS). To provide a computationally efficient alternative, we introduce HRRRCast, a data-driven emulator built with advanced machine learning techniques. HRRRCast includes two architectures: a ResNet-based model (ResHRRR) and a Graph Neural Network-based model (GraphHRRR). ResHRRR utilizes convolutional neural networks enhanced with squeeze-and-excitation blocks and Feature-wise Linear Modulation, and supports probabilistic forecasting via the Denois-ing Diffusion Implicit Model (DDIM). To better handle longer lead times, we train a single model to predict multiple lead times (1h, 3h, and 6h), and then use a greedy rollout strategy during inference. When evaluated on composite reflectivity over the full CONUS domain using ensembles of 3 to 10 members, ResHRRR outperforms HRRR forecast at light rainfall threshold (20 dBZ) and achieves competitive performance at moderate thresholds (30 dBZ). Our work advances the pioneering StormCast model described in Pathak et al. [21] by: a) training on the full CONUS domain, b) training on multiple lead times to improve long-range performance, c) using analysis data for training instead of the +1h post-analysis data inadvertently used in StormCast, and d) incorporating future Global Forecast System (GFS) weather states as inputs, adding a downscaling component that significantly improves long-lead forecast accuracy. Grid-based, neighborhood-based, and object-based verification metrics confirm improved storm placement, lower frequency bias, and enhanced success ratios compared to HRRR. Additionally, HRRRCast's ensemble forecasts maintain sharper spatial detail and reduced blurriness than deterministic baselines, with power spectra more closely matching HRRR analysis. While GraphHRRR underperforms in its current form, it lays the groundwork for future probabilistic graph-based forecasting. Overall, HRRRCast represents a step toward efficient, data-driven regional weather prediction with competitive accuracy and ensemble capability. Introduction Recent advances in machine learning weather prediction (MLWP) have shown great promise in complementing or even replacing traditional numerical weather prediction (NWP) systems, particularly at global scales. Several studies have demonstrated that data-driven models can rival the skill of physics-based models at a fraction of the computational cost, enabling applications such as ensemble forecasting and climate downscaling with greater efficiency [2, 12, 13, 23, 18, 17]. However, while progress in global MLWP is substantial, the transition to high-resolution regional forecasting-especially at convection-allowing scales (km-scale) - remains an active area of research. These authors have made equal contributions.

An Explainable Boosting Machine (EBM) is an interpretable machine learning (ML) algorithm that has benefits in high risk applications but has not yet found much use in atmospheric science. The overall goal of this work is twofold: (1) explore the use of EBMs, in combination with feature engineering, to obtain interpretable, physics-based machine learning algorithms for meteorological applications; (2) illustrate these methods for the detection of overshooting top (OTs) in satellite imagery. Specifically, we seek to simplify the process of OT detection by first using mathematical methods to extract key features, such as cloud texture using Gray-Level Co-occurrence Matrices, followed by applying an EBM. Our EBM focuses on the classification task of predicting OT regions, utilizing Channel 2 (visible imagery) and Channel 13 (infrared imagery) of the Advanced Baseline Imager sensor of the Geostationary Operational Environmental Satellite 16. Multi-Radar/Multi-Sensor system convection flags are used as labels to train the EBM model. Note, however, that detecting convection, while related, is different from detecting OTs. Once trained, the EBM was examined and minimally altered to more closely match strategies used by domain scientists to identify OTs. The result of our efforts is a fully interpretable ML algorithm that was developed in a human-machine collaboration. While the final model does not reach the accuracy of more complex approaches, it performs well and represents a significant step toward building fully interpretable ML algorithms for this and other meteorological applications.