Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out-of-distribution inputs. In this exploratory review, we explore the possibilities and limits of adversarial attacks for explainable machine learning models. First, we extend the notion of adversarial examples to fit in explainable machine learning scenarios, in which the inputs, the output classifications and the explanations of the model's decisions are assessed by humans. Next, we propose a comprehensive framework to study whether (and how) adversarial examples can be generated for explainable models under human assessment, introducing and illustrating novel attack paradigms. In particular, our framework considers a wide range of relevant yet often ignored factors such as the type of problem, the user expertise or the objective of the explanations, in order to identify the attack strategies that should be adopted in each scenario to successfully deceive the model (and the human). The intention of these contributions is to serve as a basis for a more rigorous and realistic study of adversarial examples in the field of explainable machine learning.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. The International Seabed Authority -- the United Nations body that regulates the world's ocean floor -- is preparing to resume negotiations that could open the international seabed for mining, including for materials critical for the green energy transition. Years long negotiations are reaching a critical point where the authority will soon need to begin accepting mining permit applications, adding to worries over the potential impacts on sparsely researched marine ecosystems and habitats of the deep sea. Here's a look at what deep sea mining is, why some companies and countries are applying for permits to carry it out and why environmental activists are raising concerns.

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts, but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this manuscript, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them to their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, out of 24 different model architecture, parameter count, and prediction task combinations, only one saw a statistically significant performance deficit in randomly wired networks compared to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.

Transfer learning transfers the knowledge acquired by a model from a source task to multiple downstream target tasks with minimal fine-tuning. The success of transfer learning at improving performance, especially with the use of large pre-trained models has made transfer learning an essential tool in the machine learning toolbox. However, the conditions under which the performance is transferable to downstream tasks are not understood very well. In this work, we analyze the transfer of performance for classification tasks, when only the last linear layer of the source model is fine-tuned on the target task. We propose a novel Task Transfer Analysis approach that transforms the source distribution (and classifier) by changing the class prior distribution, label, and feature spaces to produce a new source distribution (and classifier) and allows us to relate the loss of the downstream task (i.e., transferability) to that of the source task. Concretely, our bound explains transferability in terms of the Wasserstein distance between the transformed source and downstream task's distribution, conditional entropy between the label distributions of the two tasks, and weighted loss of the source classifier on the source task. Moreover, we propose an optimization problem for learning the transforms of the source task to minimize the upper bound on transferability. We perform a large-scale empirical study by using state-of-the-art pre-trained models and demonstrate the effectiveness of our bound and optimization at predicting transferability. The results of our experiments demonstrate how factors such as task relatedness, pretraining method, and model architecture affect transferability.

Researchers are increasingly using small, autonomous underwater robots to collect data in the world's oceans. Rescuers spotted debris from the tourist submarine Titan on the ocean floor near the wreck of the Titanic on June 22, 2023, indicating that the vessel suffered a catastrophic failure and the five people aboard were killed. Bringing people to the bottom of the deep ocean is inherently dangerous. At the same time, climate change means collecting data from the world's oceans is more vital than ever. Purdue University mechanical engineer Nina Mahmoudian explains how researchers reduce the risks and costs associated with deep-sea exploration: Send down subs, but keep people on the surface.

Russia has started tactical fighter jet exercises over the Baltic Sea with the goal of testing readiness to perform combat and other special operations, the country's defence ministry has said, a day after Moscow said its jets had scrambled to intercept United Kingdom military planes over the Black Sea. "The main goal of the exercise is to test the readiness of the flight crew to perform combat and special tasks as intended," Russia's defence ministry said on Tuesday. "The crews of the Su-27 [fighter jets] of the Baltic Fleet fired from airborne weapons at cruise missiles and mock enemy aircraft," the ministry announced on the Telegram messaging channel, adding that as well as improving skills, Russian fighter pilots are on "round-the-clock combat duty" guarding the air space of Russia's Kaliningrad exclave. Wedged between Poland and Lithuania on the Baltic coast, Kaliningrad is Moscow's westernmost state and was part of Germany until the end of World War II. Given to the Soviet Union at the Potsdam Conference in 1945, the enclave has roughly 1 million residents – mainly Russians but also a small number of Ukrainians, Poles and Lithuanians.

Significant wave height forecasting is a key problem in ocean data analytics. Predicting the significant wave height is crucial for estimating the energy production from waves. Moreover, the timely prediction of large waves is important to ensure the safety of maritime operations, e.g. passage of vessels. We frame the task of predicting extreme values of significant wave height as an exceedance probability forecasting problem. Accordingly, we aim at estimating the probability that the significant wave height will exceed a predefined threshold. This task is usually solved using a probabilistic binary classification model. Instead, we propose a novel approach based on a forecasting model. The method leverages the forecasts for the upcoming observations to estimate the exceedance probability according to the cumulative distribution function. We carried out experiments using data from a buoy placed in the coast of Halifax, Canada. The results suggest that the proposed methodology is better than state-of-the-art approaches for exceedance probability forecasting.

Machine learning methods for the construction of data-driven reduced order model models are used in an increasing variety of engineering domains, especially as a supplement to expensive computational fluid dynamics for design problems. An important check on the reliability of surrogate models is Uncertainty Quantification (UQ), a self assessed estimate of the model error. Accurate UQ allows for cost savings by reducing both the required size of training data sets and the required safety factors, while poor UQ prevents users from confidently relying on model predictions. We examine several machine learning techniques, including both Gaussian processes and a family UQ-augmented neural networks: Ensemble neural networks (ENN), Bayesian neural networks (BNN), Dropout neural networks (D-NN), and Gaussian neural networks (G-NN). We evaluate UQ accuracy (distinct from model accuracy) using two metrics: the distribution of normalized residuals on validation data, and the distribution of estimated uncertainties. We apply these metrics to two model data sets, representative of complex dynamical systems: an ocean engineering problem in which a ship traverses irregular wave episodes, and a dispersive wave turbulence system with extreme events, the Majda-McLaughlin-Tabak model.

Marine litter poses significant threats to marine and coastal environments, with its impacts ever-growing. Remote sensing provides an advantageous supplement to traditional mitigation techniques, such as local cleaning operations and trawl net surveys, due to its capabilities for extensive coverage and frequent observation. In this study, we used Radiative Transfer Model (RTM) simulated data and data from the Multispectral Instrument (MSI) of the Sentinel-2 mission in combination with machine learning algorithms. Our aim was to study the spectral behavior of marine plastic pollution and evaluate the applicability of RTMs within this research area. The results from the exploratory analysis and unsupervised classification using the KMeans algorithm indicate that the spectral behavior of pollutants is influenced by factors such as the type of polymer and pixel coverage percentage. The findings also reveal spectral characteristics and trends of association and differentiation among elements. The applied methodology is strongly dependent on the data, and if reapplied in new, more diverse, and detailed datasets, it can potentially generate even better results. These insights can guide future research in remote sensing applications for detecting marine plastic pollution.

First Coast Guard District Rear Admiral John Mauger offers his condolences to the loved ones of the Titan submersible crew on'America Reports.' BOSTON – EXCLUSIVE: Stockton Rush, the 61-year-old adventurer and CEO who died this week along with four other crew members in a catastrophic implosion near the bow of the Titanic, appeared in a series of never-before-seen surreal images captured during testing of the vehicle years ago. In the series of May 2018 photos taken in Abaco, Bahamas, and obtained by Fox News Digital, Rush can be seen peering through the vessel's lone porthole, testing out computer equipment inside and posing next to the 21-foot submersible on the deck of a ship before the test run. They were captured by underwater photographer Becky Kagan Schott, who said Rush had tested the vehicle numerous times in the area, and she befriended the adventurer. The Titan was designed to reach depths of 4,000 meters, according to OceanGate, the company Rush founded in 2009. It was meant for a variety of purposes, including scientific research, media production, and site surveying.