Prior work in standardized science exams requires support from large text corpus, such as targeted science corpus from Wikipedia or SimpleWikipedia. However, retrieving knowledge from the large corpus is time-consuming and questions embedded in complex semantic representation may interfere with retrieval. Inspired by the dual process theory in cognitive science, we propose a MetaQA framework, where system 1 is an intuitive meta-classifier and system 2 is a reasoning module. Specifically, our method based on meta-learning method and large language model BERT, which can efficiently solve science problems by learning from related example questions without relying on external knowledge bases. We evaluate our method on AI2 Reasoning Challenge (ARC), and the experimental results show that meta-classifier yields considerable classification performance on emerging question types. The information provided by meta-classifier significantly improves the accuracy of reasoning module from 46.6% to 64.2%, which has a competitive advantage over retrieval-based QA methods.

The Cpp-Taskflow project addresses the long-standing question: How can we make it easier for developers to write parallel and heterogeneous programs with high performance and simultaneous high productivity? Cpp-Taskflow develops a simple and powerful task programming model to enable efficient implementations of heterogeneous decomposition strategies. Our programming model empowers users with both static and dynamic task graph constructions to incorporate a broad range of computational patterns including hybrid CPU-GPU computing, dynamic control flow, and irregularity. We develop an efficient heterogeneous work-stealing strategy that adapts worker threads to available task parallelism at any time during the graph execution. We have demonstrated promising performance of Cpp-Taskflow on both micro-benchmark and real-world applications. As an example, we solved a large machine learning workload by up to 1.5x faster, 1.6x less memory, and 1.7x fewer lines of code than two industrial-strength systems, oneTBB and StarPU, on a machine of 40 CPUs and 4 GPUs.

In their article, "Egalitarianism under Severe Uncertainty", Philosophy and Public Affairs, 46:3, 2018, Thomas Rowe and Alex Voorhoeve develop an original moral decision theory for cases under uncertainty, called "pluralist egalitarianism under uncertainty". In this paper, I firstly sketch their views and arguments. I then elaborate on their moral decision theory by discussing how it applies to choice scenarios in health ethics. Finally, I suggest a new two-stage Ellsberg thought experiment challenging the core of the principle of their theory. In such an experiment pluralist egalitarianism seems to suggest the wrong, morally and rationally speaking, course of action -- no matter whether I consider my thought experiment in a simultaneous or a sequential setting.

Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification. We introduce an algorithm based on partitioning the verification problem in an iterative manner and explore two partitioning strategies, that work by partitioning the input space or by case splitting on the phases of the neuron activations, respectively. We also introduce a highly parallelizable pre-processing algorithm that uses the neuron activation phases to simplify the neural network verification problems. An extensive experimental evaluation shows the benefit of these techniques on both existing benchmarks and new benchmarks from the aviation domain. A preliminary experiment with ultra-scaling our algorithm using a large distributed cloud-based platform also shows promising results.

One of the key difficulties in using estimation-of-distribution algorithms is choosing the population sizes appropriately: Too small values lead to genetic drift, which can cause enormous difficulties. In the regime with no genetic drift, however, often the runtime is roughly proportional to the population size, which renders large population sizes inefficient. Based on a recent quantitative analysis which population sizes lead to genetic drift, we propose a parameter-less version of the compact genetic algorithm that automatically finds a suitable population size without spending too much time in situations unfavorable due to genetic drift. We prove an easy mathematical runtime guarantee for this algorithm and conduct an extensive experimental analysis on four classic benchmark problems. The former shows that under a natural assumption, our algorithm has a performance similar to the one obtainable from the best population size. The latter confirms that missing the right population size can be highly detrimental and shows that our algorithm as well as a previously proposed parameter-less one based on parallel runs avoids such pitfalls. Comparing the two approaches, ours profits from its ability to abort runs which are likely to be stuck in a genetic drift situation.

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods hide but fail to truly remove the biases, which can still be observed in word nearest-neighbor statistics. In this work we propose a probabilistic view of word embedding bias. We leverage this framework to present a novel method for mitigating bias which relies on probabilistic observations to yield a more robust bias mitigation algorithm. We demonstrate that this method effectively reduces bias according to three separate measures of bias while maintaining embedding quality across various popular benchmark semantic tasks.

As the COVID-19 pandemic rages on unabated in countries around the world, there's a shared desire among those forced to shelter in place to see the extent to which social distancing is slowing the disease's spread. It's understandable -- collateral damage from government-imposed business closures threatens to devastate entire industries. As of this week, 26 million Americans have filed for unemployment claims, according to the U.S. Bureau of Labor Statistics, and the International Monetary Fund predicts a global financial crisis rivaling the Great Depression. Fortunately, a preprint study published by researchers at the University of Texas, the Southwest Research Institute, and the University of Texas Health Science Center in San Antonio strongly implies that quarantining and physical distancing are having the intended effects. Using a hybrid AI system dubbed SIRNet and several epidemiological models, which were trained on smartphone location data along with population-weighted density and other data points from the startup Safe Graph, World Health Organization, the U.S. Centers for Disease Control and Prevention, and elsewhere, the coauthors claim they managed to accurately predict the outcomes of various social distancing policies.

AI healthcare startup Babylon Health believes it can appropriately triage patients in 85 percent of cases. Babylon Health is best known for GP at Hand, a service which is supported by UK health secretary Matt Hancock and integrated into Samsung Health. GP at Hand links patients with health experts 24/7 using video calls and can facilitate any prescriptions to be sent to local pharmacies. The service, however, has been criticised for an AI chatbot which repeatedly gave unsafe advice and for only taking on healthier, often younger individuals while redirecting cash away from local surgeries relied on by older and sicker patients. Correct triaging is essential to ensure patients receive the appropriate care.

A new AI system developed by researchers from Google and the University of California could prevent deaths caused by incorrect prescriptions. While quite rare, prescriptions that are incorrect – or react badly to a patient's existing medications – can result in hospitalisation or even death. In a blog post today, Alvin Rajkomar MD, Research Scientist and Eyal Oren PhD, Product Manager, Google AI, set out their work on using AI for medical predictions. The AI is able to predict which conditions a patient is being treated for based on certain parameters. "For example, if a doctor prescribed ceftriaxone and doxycycline for a patient with an elevated temperature, fever and cough, the model could identify these as signals that the patient was being treated for pneumonia," the researchers wrote.

In the past few years, AI has advanced our technology at an incredible rate. From completely automating labor-intensive jobs to diagnosing lung cancer, AI has achieved feats previously thought impossible. However, in the wrong hands, an algorithm can be a destructive weapon. To ensure that malicious actors don't wreak havoc in our society, there are several key challenges which we have to solve. The real danger of AI is not the rise of a sentient algorithm like SkyNet taking over the world.