In many real-world scenarios, the time it takes for a mobile agent, e.g., a robot, to move from one location to another may vary due to exogenous events and be difficult to predict accurately. Planning in such scenarios is challenging, especially in the context of Multi-Agent Pathfinding (MAPF), where the goal is to find paths to multiple agents and temporal coordination is necessary to avoid collisions. In this work, we consider a MAPF problem with this form of time uncertainty, where we are only given upper and lower bounds on the time it takes each agent to move. The objective is to find a safe solution, which is a solution that can be executed by all agents and is guaranteed to avoid collisions. We propose two complete and optimal algorithms for finding safe solutions based on well-known MAPF algorithms, namely, A* with Operator Decomposition (A* + OD) and Conflict-Based Search (CBS). Experimentally, we observe that on several standard MAPF grids the CBS-based algorithm performs better. We also explore the option of online replanning in this context, i.e., modifying the agents' plans during execution, to reduce the overall execution cost. We consider two online settings: (a) when an agent can sense the current time and its current location, and (b) when the agents can also communicate seamlessly during execution. For each setting, we propose a replanning algorithm and analyze its behavior theoretically and empirically. Our experimental evaluation confirms that indeed online replanning in both settings can significantly reduce solution cost.

Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-parameterized, causing many difficulties in training, prediction and interpretation. We propose a frequentist-like method for learning sparse DNNs and justify its consistency under the Bayesian framework: the proposed method could learn a sparse DNN with at most $O(n/\log(n))$ connections and nice theoretical guarantees such as posterior consistency, variable selection consistency and asymptotically optimal generalization bounds. In particular, we establish posterior consistency for the sparse DNN with a mixture Gaussian prior, show that the structure of the sparse DNN can be consistently determined using a Laplace approximation-based marginal posterior inclusion probability approach, and use Bayesian evidence to elicit sparse DNNs learned by an optimization method such as stochastic gradient descent in multiple runs with different initializations. The proposed method is computationally more efficient than standard Bayesian methods for large-scale sparse DNNs. The numerical results indicate that the proposed method can perform very well for large-scale network compression and high-dimensional nonlinear variable selection, both advancing interpretable machine learning.

As the number of fatal crashes involving truck drivers increases, one company believes artificial intelligence (AI) could help. It may look like a standard mini-tanker, but a small camera in the truck's cab could be a lifesaver. The AI device scans the driver's eyes to detect signs of fatigue and distraction, and if their eye lids close for one and a half seconds, an alarm sounds and the driver's seat will vibrate. A camera also records the moment. "What this technology is about is keeping the driver focussed on the road, and alerting them for any reason if their attention is drawn away," said Charles Dawson, the chief executive of Autosense.

A few days before racing in the 36th match for the America's Cup, the covers have been lifted on the testing and development process, using Artificial Intelligence employed by Emirates Team New Zealand, and developed in conjunction with one of worlds most prestigious consulting firms McKinsey & Company. While the team's use of simulators has been widely discussed, and one is on display at the America's Cup Village. The team has been working with McKinsey subsidiary Quantum Black to develop a "digital twin" of the team's AC75 that used a process of machine learning to perform many more iterations of a sailing situation than was possible using human crew, and to come up with options that were faster than the crew was currently achieving. AI Bots work particularly well when there is large volume of data. The Bot is programmed to self-learn from its own analysis.

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific parameters. The global parameters are fixed across tasks whereas the task specific parameters act as local adapters for each task, and help in efficiently transforming the previous task's feature map to the new task's feature map. Moreover, we propose an element-wise residual bias in the transformed feature space which highly stabilizes GAN training. In contrast to the recent approaches for continual GANs, we do not rely on memory replay, regularization towards previous tasks' parameters, or expensive weight transformations. Through extensive experiments on challenging and diverse datasets, we show that the feature-map transformation based approach outperforms state-of-the-art continual GANs methods, with substantially fewer parameters, and also generates high-quality samples that can be used in generative replay based continual learning of discriminative tasks.

There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level explainability, this machine needs to provide human causally understandable explanations, also known as causability. A specific class of algorithms that have the potential to provide causability are counterfactuals. This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence. We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles. This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data. This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human decision-maker. Our findings suggest that the explanations derived from major algorithms in the literature provide spurious correlations rather than cause/effects relationships, leading to sub-optimal, erroneous or even biased explanations. This paper also advances the literature with new directions and challenges on promoting causability in model-agnostic approaches for explainable artificial intelligence.

Consensus maximisation (MaxCon), which is widely used for robust fitting in computer vision, aims to find the largest subset of data that fits the model within some tolerance level. In this paper, we outline the connection between MaxCon problem and the abstract problem of finding the maximum upper zero of a Monotone Boolean Function (MBF) defined over the Boolean Cube. Then, we link the concept of influences (in a MBF) to the concept of outlier (in MaxCon) and show that influences of points belonging to the largest structure in data would generally be smaller under certain conditions. Based on this observation, we present an iterative algorithm to perform consensus maximisation. Results for both synthetic and real visual data experiments show that the MBF based algorithm is capable of generating a near optimal solution relatively quickly. This is particularly important where there are large number of outliers (gross or pseudo) in the observed data.

We introduce the task of changing the narrative point of view, where characters are assigned a narrative perspective that is different from the one originally used by the writer. The resulting shift in the narrative point of view alters the reading experience and can be used as a tool in fiction writing or to generate types of text ranging from educational to self-help and self-diagnosis. We introduce a benchmark dataset containing a wide range of types of narratives annotated with changes in point of view from deictic (first or second person) to anaphoric (third person) and describe a pipeline for processing raw text that relies on a neural architecture for mention selection. Evaluations on the new benchmark dataset show that the proposed architecture substantially outperforms the baselines by generating mentions that are less ambiguous and more natural.

Three years ago, Customs and Border Protection placed an order for self-flying aircraft that could launch on their own, rendezvous, locate and monitor multiple targets on the ground without any human intervention. In its reasoning for the order, CBP said the level of monitoring required to secure America's long land borders from the sky was too cumbersome for people alone. To research and build the drones, CBP handed $500,000 to Mitre Corp., a trusted nonprofit Skunk Works that was already furnishing border police with prototype rapid DNA testing and smartwatch hacking technology. They were "tested but not fielded operationally" as "the gap from simulation to reality turned out to be much larger than the research team originally envisioned," a CBP spokesperson says. This year, America's border police will test automated drones from Skydio, the Redwood City, Calif.-based startup that on Monday announced it had raised an additional $170 million in venture funding at a valuation of $1 billion. That brings the total raised for Skydio to $340 million.

WHEN IT comes to using artificial intelligence (AI), intelligence agencies have been at it longer than most. In the cold war America's National Security Agency (NSA) and Britain's Government Communications Headquarters (GCHQ) explored early AI to help transcribe and translate the enormous volumes of Soviet phone-intercepts they began hoovering up in the 1960s and 1970s. Your browser does not support the audio element. Yet the technology was immature. One former European intelligence officer says his service did not use automatic transcription or translation in Afghanistan in the 2000s, relying on native speakers instead.