Deep learning has been highly successful in some applications. Nevertheless, its use for solving partial differential equations (PDEs) has only been of recent interest with current state-of-the-art machine learning libraries, e.g., TensorFlow or PyTorch. Physics-informed neural networks (PINNs) are an attractive tool for solving partial differential equations based on sparse and noisy data. Here extend PINNs to solve obstacle-related PDEs which present a great computational challenge because they necessitate numerical methods that can yield an accurate approximation of the solution that lies above a given obstacle. The performance of the proposed PINNs is demonstrated in multiple scenarios for linear and nonlinear PDEs subject to regular and irregular obstacles.

"My views are my own, as are my biases." That's how Leslie Miley, investor, ex-Googler, and former CTO of the Obama Foundation, kicked off his QCon London keynote. But can the same be said for generative artificial intelligence (AI)? Not likely, as collective biases are baked in at scale, influencing everyone's views. If it keeps going unchecked, it will have devastating effects both on the Earth and the people living on it.

We consider the solution to large stochastic control problems by means of methods that rely on compact representations and a vari(cid:173) ant of the value iteration algorithm to compute approximate cost(cid:173) to-go functions. While such methods are known to be unstable in general, we identify a new class of problems for which convergence, as well as graceful error bounds, are guaranteed. This class in(cid:173) volves linear parameterizations of the cost-to- go function together with an assumption that the dynamic programming operator is a contraction with respect to the Euclidean norm when applied to functions in the parameterized class. We provide a special case where this assumption is satisfied, which relies on the locality of transitions in a state space. Other cases will be discussed in a full length version of this paper.

It's not often you meet someone who's genuinely changed the world, but that's what happens the day I greet Niantic CEO John Hanke. Sipping his coffee alone in a gargantuan San Franciscan boardroom, I wonder whether the man on the other end of this Zoom call realises just how often people use his former company's creation, Google Maps. Hanke's yearning to create started young. Fresh out of business school in the 1990s and already with one of the first online gaming successes to his name, he was snapped up – along with his company, Keyhole, by Google founders Larry Page and Sergey Brin, and folded into the team that made Google Maps, now arguably the most useful thing on your smartphone. "None of us were interested in doing the thing where you got your driving directions, printed them out and took it with you on a sheet of paper," Hanke says.

Flexible road pavements deteriorate primarily due to traffic and adverse environmental conditions. Cracking is the most common deterioration mechanism; the surveying thereof is typically conducted manually using internationally defined classification standards. In South Africa, the use of high-definition video images has been introduced, which allows for safer road surveying. However, surveying is still a tedious manual process. Automation of the detection of defects such as cracks would allow for faster analysis of road networks and potentially reduce human bias and error. This study performs a comparison of six state-of-the-art convolutional neural network models for the purpose of crack detection. The models are pretrained on the ImageNet dataset, and fine-tuned using a new real-world binary crack dataset consisting of 14000 samples. The effects of dataset augmentation are also investigated. Of the six models trained, five achieved accuracy above 97%. The highest recorded accuracy was 98%, achieved by the ResNet and VGG16 models. The dataset is available at the following URL: https://zenodo.org/record/7795975

Question answering (QA) models have shown compelling results in the task of Machine Reading Comprehension (MRC). Recently these systems have proved to perform better than humans on held-out test sets of datasets e.g. SQuAD, but their robustness is not guaranteed. The QA model's brittleness is exposed when evaluated on adversarial generated examples by a performance drop. In this study, we explore the robustness of MRC models to entity renaming, with entities from low-resource regions such as Africa. We propose EntSwap, a method for test-time perturbations, to create a test set whose entities have been renamed. In particular, we rename entities of type: country, person, nationality, location, organization, and city, to create AfriSQuAD2. Using the perturbed test set, we evaluate the robustness of three popular MRC models. We find that compared to base models, large models perform well comparatively on novel entities. Furthermore, our analysis indicates that entity type person highly challenges the MRC models' performance.

Machine Learning (ML) techniques can facilitate the automation of malicious software (malware for short) detection, but suffer from evasion attacks. Many studies counter such attacks in heuristic manners, lacking theoretical guarantees and defense effectiveness. In this paper, we propose a new adversarial training framework, termed Principled Adversarial Malware Detection (PAD), which offers convergence guarantees for robust optimization methods. PAD lays on a learnable convex measurement that quantifies distribution-wise discrete perturbations to protect malware detectors from adversaries, whereby for smooth detectors, adversarial training can be performed with theoretical treatments. To promote defense effectiveness, we propose a new mixture of attacks to instantiate PAD to enhance deep neural network-based measurements and malware detectors. Experimental results on two Android malware datasets demonstrate: (i) the proposed method significantly outperforms the state-of-the-art defenses; (ii) it can harden ML-based malware detection against 27 evasion attacks with detection accuracies greater than 83.45%, at the price of suffering an accuracy decrease smaller than 2.16% in the absence of attacks; (iii) it matches or outperforms many anti-malware scanners in VirusTotal against realistic adversarial malware.

A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast MCMC sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

Poverty maps are essential tools for governments and NGOs to track socioeconomic changes and adequately allocate infrastructure and services in places in need. Sensor and online crowd-sourced data combined with machine learning methods have provided a recent breakthrough in poverty map inference. However, these methods do not capture local wealth fluctuations, and are not optimized to produce accountable results that guarantee accurate predictions to all sub-populations. Here, we propose a pipeline of machine learning models to infer the mean and standard deviation of wealth across multiple geographically clustered populated places, and illustrate their performance in Sierra Leone and Uganda. These models leverage seven independent and freely available feature sources based on satellite images, and metadata collected via online crowd-sourcing and social media. Our models show that combined metadata features are the best predictors of wealth in rural areas, outperforming image-based models, which are the best for predicting the highest wealth quintiles. Our results recover the local mean and variation of wealth, and correctly capture the positive yet non-monotonous correlation between them. We further demonstrate the capabilities and limitations of model transfer across countries and the effects of data recency and other biases. Our methodology provides open tools to build towards more transparent and interpretable models to help governments and NGOs to make informed decisions based on data availability, urbanization level, and poverty thresholds.

Millions have dreamt about driving across the US -- but now science has taken the guesswork out of planning the epic trip. An Orgeon-based data scientist used a sophisticated algorithm to generate the perfect journey, factoring in things like logistics for traffic and the most scenic routes for a three-month vacation. Each stop is a national natural landmark, national historic site, national park or national monument, all in the lower 48 states. In total the route boasts 50 iconic sights. The 13,699-mile-long route stops at Mount Rushmore, the San Francisco Cable Cars, Cape Canaveral Air Force Station and other well-known spots.