We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answers learned from imitating human texts. We tested GPT-3, GPT-Neo/J, GPT-2 and a T5-based model. The best model was truthful on 58% of questions, while human performance was 94%. Models generated many false answers that mimic popular misconceptions and have the potential to deceive humans. The largest models were generally the least truthful. For example, the 6B-parameter GPT-J model was 17% less truthful than its 125M-parameter counterpart. This contrasts with other NLP tasks, where performance improves with model size. However, this result is expected if false answers are learned from the training distribution. We suggest that scaling up models alone is less promising for improving truthfulness than fine-tuning using training objectives other than imitation of text from the web.

The crew of SpaceX's Inspiration4, the first all-civilian spaceflight to orbit, will be used to collect a huge amount of health data that will be used to help future humans travel off-planet. The four humans riding the Dragon capsule are US billionaire Jared Isaacman, who commissioned the flight, St. Jude physician's assistant Hayley Arcenaux, data engineer Chris Sembroski and geoscientist and artist Sian Proctor. The mission, scheduled for 15 September, will orbit the planet at 575 kilometres for three days before returning to Earth, descending into the Atlantic Ocean. This is the furthest distance from Earth for any human spaceflight since the Hubble Space Telescope repair missions, SpaceX says. The crew will collect a range of medical data including ECG (electrocardiograph) activity, movement, sleep, heart rate and rhythm, blood oxygen saturation, cabin noise and light intensity – which will be used to help assess changes in behavioural and cognitive performance over time.

Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. However, there is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting (CEF). Our framework combines two formalisms: a) symbolic automata which are used to encode complex event patterns; and b) prediction suffix trees which can provide a succinct probabilistic description of an automaton's behavior. We compare our proposed approach against state-of-the-art methods and show its advantage in terms of accuracy and efficiency. In particular, prediction suffix trees, being variable-order Markov models, have the ability to capture long-term dependencies in a stream by remembering only those past sequences that are informative enough. Our experimental results demonstrate the benefits, in terms of accuracy, of being able to capture such long-term dependencies. This is achieved by increasing the order of our model beyond what is possible with full-order Markov models that need to perform an exhaustive enumeration of all possible past sequences of a given order. We also discuss extensively how CEF solutions should be best evaluated on the quality of their forecasts.

If it looks like a penguin and swims like a penguin – but it's actually a robot – then it must be the latest advance in marine sensory equipment. The Quadroin is an autonomous underwater vehicle (AUV): a 3D-printed self-propelled machine designed to mimic a penguin in order to measure the properties of oceanic eddies. It was developed by Burkard Baschek while head of Germany's Institute of Coastal Ocean Dynamics at the Helmholtz Centre Hereon in Geesthacht after he watched more than $20,000 of his equipment sink to the bottom of the Pacific Ocean. Eddies are small ocean currents that other research methods have struggled to capture. They influence all the animals and plants in the seas as well as the Earth's climate, driving roughly 50% of all phytoplankton production.

On a recent afternoon in Maracaibo, Venezuela, Alexander Marinez, who has short-cropped black hair and three-to-four-day stubble, sat in front of his computer tracking herbiboars in the mushroom forests on Fossil Island. He pressed down on his glowing mouse, the newest addition to his otherwise timeworn gaming setup. The pixelated character on his computer screen followed the tracks of a hedgehoglike creature with triangular tusks and herbs growing out of its back. Outside Marinez's one-story house, the sun bore down on the dirt road. His home lies about six miles away from the strait that connects the Caribbean Sea with Lake Maracaibo, one of the world's richest sources of oil. The character inspected a tunnel. Suddenly, the herbiboar appeared, and the character attacked, stunning it.

In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more, the model can be ruined due to the domain shift between training data and testing data. Text recognition is a broadly studied field in computer vision and suffers from the same problems noted above due to the diversity of fonts and complicated backgrounds. In this paper, we focus on the text recognition problem and mainly make three contributions toward these problems. First, we collect a multi-source domain adaptation dataset for text recognition, including five different domains with over five million images, which is the first multi-domain text recognition dataset to our best knowledge. Secondly, we propose a new method called Meta Self-Learning, which combines the self-learning method with the meta-learning paradigm and achieves a better recognition result under the scene of multi-domain adaptation. Thirdly, extensive experiments are conducted on the dataset to provide a benchmark and also show the effectiveness of our method. The code of our work and dataset are available soon at https://bupt-ai-cz.github.io/Meta-SelfLearning/.

Significant to economic stability across the world, the current scenario in the aqua-farming industry is far from what it was a decade ago. With fewer changes in people and processes, the growth and evolution of the aqua-farming sector have been steady in the past decade. Although the technological advancements have been limited, yet the onset of IoT has triggered the introduction of AI-based process adoptions and automation. The sector is fairly large and deals with the production, and supply of aquatic animals. Fish, shrimp, oysters, and algae farming are closely associated with the global food industry.

Manifold-valued functional data analysis (FDA) recently becomes an active area of research motivated by the raising availability of trajectories or longitudinal data observed on non-linear manifolds. The challenges of analyzing such data come from many aspects, including infinite dimensionality and nonlinearity, as well as time-domain or phase variability. In this paper, we study the amplitude part of manifold-valued functions on $\mathbb{S}^2$, which is invariant to random time warping or re-parameterization. Utilizing the nice geometry of $\mathbb{S}^2$, we develop a set of efficient and accurate tools for temporal alignment of functions, geodesic computing, and sample mean calculation. At the heart of these tools, they rely on gradient descent algorithms with carefully derived gradients. We show the advantages of these newly developed tools over its competitors with extensive simulations and real data and demonstrate the importance of considering the amplitude part of functions instead of mixing it with phase variability in manifold-valued FDA.

"We know that flooding has been getting worse," said study lead author Frances Davenport, a PhD student in Earth system science in Stanford's School of Earth, Energy & Environmental Sciences (Stanford Earth). "Our goal was to understand why extreme precipitation is increasing, which in turn could lead to better predictions about future flooding." Among other impacts, global warming is expected to drive heavier rain and snowfall by creating a warmer atmosphere that can hold more moisture. Scientists hypothesize that climate change may affect precipitation in other ways, too, such as changing when and where storms occur. Revealing these impacts has remained difficult, however, in part because global climate models do not necessarily have the spatial resolution to model these regional extreme events.

From lake-draining drought in California to bridge-breaking floods in China, extreme weather is wreaking havoc. Preparing for weather extremes in a changing climate remains a challenge, however, because their causes are complex and their response to global warming is often not well understood. Now, Stanford researchers have developed a machine learning tool to identify conditions for extreme precipitation events in the Midwest, which account for over half of all major U.S. flood disasters. Published in Geophysical Research Letters, their approach is one of the first examples using AI to analyze causes of long-term changes in extreme events and could help make projections of such events more accurate. "We know that flooding has been getting worse," said study lead author Frances Davenport, a Ph.D. student in Earth system science in Stanford's School of Earth, Energy & Environmental Sciences (Stanford Earth).