Herding-- one of humanity's most foundational ways of life--is a pillar of survival in West Africa's Sahel. Migratory herders usher cattle between seasonal pastures, since they rarely own land. However, these traditional ways of doing things are becoming increasingly impossible, thanks to a complex mix of climate change, politics and war. In more recent years, various Western players touting tech trends like artificial intelligence and predictive analysis have swooped in with promises to solve the region's myriad problems. But some think there could be a much simpler solution, that puts real data directly into the herders' hands. Recent advances in data collection--both from geosatellites and from herders themselves--have generated an abundance of information on ground cover quantity and quality, water availability, rain forecasts, livestock concentrations, and more.

Doha, Qatar – At one of the world's largest technology conferences, whether it was on the main stage, its side panels, or at the dozens of glitzy, towering company booths, there was one term on everybody's lips: artificial intelligence (AI). At Web Summit – held for the first time in the Middle East in Doha – and which wrapped up on Thursday, entrepreneurs, investors and business leaders from around the world were all talking about AI's capabilities. Yet alongside that excitement, there are also growing concerns among experts that these technologies could exacerbate inequities dividing the world. Technologies, including AI, run the risk of amplifying biases that already exist, according to Ayo Tometi, co-creator of the US-based antiracist movement Black Lives Matter. "We're seeing quite literally, that prejudice is being programmed into the technologies that are being deployed in our communities. And these biases must be addressed," Tometi said at the summit.

In more recent years, various Western players touting tech trends like artificial intelligence and predictive analysis have swooped in with promises to solve the region's myriad problems. But Garbal--named after the word for a livestock market in the language of the Fulani, an ethnic group that makes up the majority of the Sahel's herders--aims to do things differently. Building on an approach pioneered by a 37-year-old American data scientist named Alex Orenstein, Garbal is focused on how humbler technologies might effectively support the 80% of Nigeriens who live off livestock and the land. "There's still this idea of'How can we use new tech?' But the tech is already there--we just need to be more intentional in applying it," Orenstein says, arguing that donor enthusiasm for shiny, complex solutions is often misplaced.

U.S. forces carried out more strikes against anti-ship cruise missiles and a drone in the Red Sea Thursday evening, Central Command said. CENTCOM forces conducted two self-defense strikes against six mobile anti-ship cruise missiles that were prepared to launch towards the Red Sea between 6 and 7:15 p.m. local time. Earlier in the evening, CENTCOM forces shot down a drone over the southern Red Sea in self-defense, CENTCOM said. "CENTCOM forces determined that the missiles and UAV presented an imminent threat to merchant vessels and to the U.S. Navy ships in the region," the command said. "These actions will protect freedom of navigation and make international waters safer and more secure for U.S. Navy and merchant vessels."

The way the UK government has been tagging migrants with GPS trackers is illegal, the country's privacy regulator ruled on Friday, in a rebuke to officials who have been experimenting with migrant-surveillance tech in both the UK and the US. As part of an 18-month pilot that concluded in December, the UK interior ministry, known as the Home Office, forced up to 600 people who arrived in the country without permission to wear ankle tags that continuously tracked their locations. However, that pilot broke UK data protection law because it did not properly assess the privacy intrusion of GPS tracking or give migrants clear information about the data that was being collected, the UK's Information Commissioner's Office (ICO) said today. The ruling means the Home Office has 28 days to update its policies around GPS tracking. Friday's decision also means the ICO could fine the Home Office up to 17.5 million ( 22 million) or 4 percent of its turnover--whichever is higher--if it resumes tagging people who arrive on the UK south coast in small boats from Europe.

What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of input-label pairs ($\textit{prototypes}$) that capture essential aspects of the original dataset. In this paper, we make the key observation that existing methods distilling into explicit prototypes are very often suboptimal, incurring in unexpected storage cost from distilled labels. In response, we propose $\textit{Distributional Dataset Distillation}$ (D3), which encodes the data using minimal sufficient per-class statistics and paired with a decoder, we distill dataset into a compact distributional representation that is more memory-efficient compared to prototype-based methods. To scale up the process of learning these representations, we propose $\textit{Federated distillation}$, which decomposes the dataset into subsets, distills them in parallel using sub-task experts and then re-aggregates them. We thoroughly evaluate our algorithm on a three-dimensional metric and show that our method achieves state-of-the-art results on TinyImageNet and ImageNet-1K. Specifically, we outperform the prior art by $6.9\%$ on ImageNet-1K under the storage budget of 2 images per class.

The robustness of human social networks against epidemic propagation relies on the propensity for physical contact adaptation. During the early phase of infection, asymptomatic carriers exhibit the same activity level as susceptible individuals, which presents challenges for incorporating control measures in epidemic projection models. This paper focuses on modeling and cost-efficient activity control of susceptible and carrier individuals in the context of the susceptible-carrier-infected-removed (SCIR) epidemic model over a two-layer contact network. In this model, individuals switch from a static contact layer to create new links in a temporal layer based on state-dependent activation rates. We derive conditions for the infection to die out or persist in a homogeneous network. Considering the significant costs associated with reducing the activity of susceptible and carrier individuals, we formulate an optimization problem to minimize the disease decay rate while constrained by a limited budget. We propose the use of successive geometric programming (SGP) approximation for this optimization task. Through simulation experiments on Poisson random graphs, we assess the impact of different parameters on disease prevalence. The results demonstrate that our SGP framework achieves a cost reduction of nearly 33% compared to conventional methods based on degree and closeness centrality.

Education plays a pivotal role in alleviating poverty, driving economic growth, and empowering individuals, thereby significantly influencing societal and personal development. However, the persistent issue of school dropout poses a significant challenge, with its effects extending beyond the individual. While previous research has employed machine learning for dropout classification, these studies often suffer from a short-term focus, relying on data collected only a few years into the study period. This study expanded the modeling horizon by utilizing a 13-year longitudinal dataset, encompassing data from kindergarten to Grade 9. Our methodology incorporated a comprehensive range of parameters, including students' academic and cognitive skills, motivation, behavior, well-being, and officially recorded dropout data. The machine learning models developed in this study demonstrated notable classification ability, achieving a mean area under the curve (AUC) of 0.61 with data up to Grade 6 and an improved AUC of 0.65 with data up to Grade 9. Further data collection and independent correlational and causal analyses are crucial. In future iterations, such models may have the potential to proactively support educators' processes and existing protocols for identifying at-risk students, thereby potentially aiding in the reinvention of student retention and success strategies and ultimately contributing to improved educational outcomes.

Unmanned Aircraft Vehicles (UAVs) are becoming a crucial tool in modern warfare, primarily due to their cost-effectiveness, risk reduction, and ability to perform a wider range of activities. The use of autonomous UAVs to conduct strike missions against highly valuable targets is the focus of this research. Due to developments in ledger technology, smart contracts, and machine learning, such activities formerly carried out by professionals or remotely flown UAVs are now feasible. Our study provides the first in-depth analysis of challenges and preliminary solutions for successful implementation of an autonomous UAV mission. Specifically, we identify challenges that have to be overcome and propose possible technical solutions for the challenges identified. We also derive analytical expressions for the success probability of an autonomous UAV mission, and describe a machine learning model to train the UAV.

Effective exploration is crucial to discovering optimal strategies for multi-agent reinforcement learning (MARL) in complex coordination tasks. Existing methods mainly utilize intrinsic rewards to enable committed exploration or use role-based learning for decomposing joint action spaces instead of directly conducting a collective search in the entire action-observation space. However, they often face challenges obtaining specific joint action sequences to reach successful states in long-horizon tasks. To address this limitation, we propose Imagine, Initialize, and Explore (IIE), a novel method that offers a promising solution for efficient multi-agent exploration in complex scenarios. IIE employs a transformer model to imagine how the agents reach a critical state that can influence each other's transition functions. Then, we initialize the environment at this state using a simulator before the exploration phase. We formulate the imagination as a sequence modeling problem, where the states, observations, prompts, actions, and rewards are predicted autoregressively. The prompt consists of timestep-to-go, return-to-go, influence value, and one-shot demonstration, specifying the desired state and trajectory as well as guiding the action generation. By initializing agents at the critical states, IIE significantly increases the likelihood of discovering potentially important under-explored regions. Despite its simplicity, empirical results demonstrate that our method outperforms multi-agent exploration baselines on the StarCraft Multi-Agent Challenge (SMAC) and SMACv2 environments. Particularly, IIE shows improved performance in the sparse-reward SMAC tasks and produces more effective curricula over the initialized states than other generative methods, such as CVAE-GAN and diffusion models.