A cross-disciplinary group of researchers used AI as part of an analysis of photos posted online that recognizes an association between happiness, life satisfaction, and nature. Researchers from universities in Australia and Singapore say the analysis demonstrates the biophilia hypothesis that humans are naturally attracted to nature and people around the world have a preference for nature in their fun activities, vacations, and honeymoons. The analysis of more than 31,000 photos also found that people in nations with high life satisfaction scores like Costa Rica and Finland tend to take a higher proportion of photographs during fun activities like weddings or recreation. Nature also appears prominently in vacation and honeymoon photos. The frequency of nature in different activities varied widely across countries.

This article is part of a special report on artificial intelligence, The AI Issue. Digital personal assistants, software that can trounce board game champions, algorithms serving up customized online advertising -- wherever you turn, artificial intelligence appears to be taking over the world. But look past the self-driving cars and facial-recognition cameras, and you'll see that the technology is a lot less intelligent than it may at first appear. It's likely to be decades, at best, before even the smartest forms of AI can outdo humans in the complex tasks that make up daily life. "The real world is a complicated, messy place," said Michael Wooldridge, program co-director at the Alan Turing Institute, the United Kingdom's national center of excellence for data science and artificial intelligence.

Speech recognition systems are deep-rooted with bias toward people of color, a new study reveals. Stanford researchers found these technologies from Amazon, Apple, Google, IBM and Microsoft make twice as many errors when interpreting language from black people than words spoken by whites. The team fed systems with nearly 2,000 speech samples from 115 individuals, 42 whites and 73 blacks, and found the average error rate for whites was 19 percent and 35 percent for blacks. Apple was found to perform the worst out of the group with a 45 percent error rate for black speakers and 23 percent for white speakers. Those involved with the study believed the inaccuracies are due to data sets used to train the systems are designed predominately by white people.

Interventions are of fundamental importance in Pearl's probabilistic causality regime. In this paper, we will inspect how interventions influence the interpretation of causation in causal models in specific situation. To this end, we will introduce a priori relationships as non-causal relationships in a causal system. Then, we will proceed to discuss the cases that interventions can lead to spurious causation interpretations. This includes the interventional detection of a priori relationships, and cases where the interventional detection of causality forms structural causal models that are not valid in natural situations. We will also discuss other properties of a priori relations and SCMs that have a priori information in their structural equations.

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS). A knowledge graph is capable of encoding high-order relations that connect two objects with one or multiple related attributes. With the help of the emerging Graph Neural Networks (GNN), it is possible to extract both object characteristics and relations from KG, which is an essential factor for successful recommendations. In this paper, we provide a comprehensive survey of the GNN-based knowledge-aware deep recommender systems. Specifically, we discuss the state-of-the-art frameworks with a focus on their core component, i.e., the graph embedding module, and how they address practical recommendation issues such as scalability, cold-start and so on. We further summarize the commonly-used benchmark datasets, evaluation metrics as well as open-source codes. Finally, we conclude the survey and propose potential research directions in this rapidly growing field.

Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.

Recently, the data-selective adaptive Volterra filters have been proposed; however, up to now, there are not any theoretical analyses on its behavior rather than numerical simulations. Therefore, in this paper, we analyze the robustness (in the sense of l 2 -stability) of the data-selective Volterra normalized least-mean-square (DS-VNLMS) algorithm. First, we study the local robustness of this algorithm at any iteration, then we propose a global bound for the error/discrepancy in the coefficient vector. Also, we demonstrate that the DS-VNLMS algorithm improves the parameter estimation for the majority of the iterations that an update is implemented. Moreover, we also prove that if the noise bound is known, then we can set the DS-VNLMS so that it never degrades the estimate. The simulation results corroborate the validity of the executed analysis and demonstrate that the DS-VNLMS algorithm is robust against noise, no matter how its parameters are adopted.

The global degradation of water resources is a matter of great concern, especially for the survival of humanity. The effective monitoring and management of existing water resources is necessary to achieve and maintain optimal water quality. The prediction of the quality of water resources will aid in the timely identification of possible problem areas and thus increase the efficiency of water management. The purpose of this research is to develop a water quality prediction model based on water quality parameters through the application of a specialised recurrent neural network (RNN), Long Short-Term Memory (LSTM) and the use of historical water quality data over several years. Both multivariate single and multiple step LSTM models were developed, using a Rectified Linear Unit (ReLU) activation function and a Root Mean Square Propagation (RMSprop) optimiser was developed. The single step model attained an error of 0.01 mg/L, whilst the multiple step model achieved a Root Mean Squared Error (RMSE) of 0.227 mg/L.

We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels. In order to address our new multimodal inference task, a model is required to possess sophisticated reasoning skills, from surface-level grounding (e.g., identifying objects and characters in the video) to in-depth commonsense reasoning (e.g., inferring causal relations of events in the video). We present a detailed analysis of the dataset and an extensive evaluation over many strong baselines, providing valuable insights on the challenges of this new task.

Scaling up the vocabulary and complexity of current visual understanding systems is necessary in order to bridge the gap between human and machine visual intelligence. However, a crucial impediment to this end lies in the difficulty of generalizing to data distributions that come from real-world scenarios. Typically such distributions follow Zipf's law which states that only a small portion of the collected object classes will have abundant examples (head); while most classes will contain just a few (tail). In this paper, we propose to study a novel task concerning the generalization of visual relationships that are on the distribution's tail, i.e. we investigate how to help AI systems to better recognize rare relationships like , where the subject S, predicate P, and/or the object O come from the tail of the corresponding distributions. To achieve this goal, we first introduce two large-scale visual-relationship detection benchmarks built upon the widely used Visual Genome and GQA datasets. We also propose an intuitive evaluation protocol that gives credit to classifiers who prefer concepts that are semantically close to the ground truth class according to wordNet- or word2vec-induced metrics. Finally, we introduce a visiolinguistic version of a Hubless loss which we show experimentally that it consistently encourages classifiers to be more predictive of the tail classes while still being accurate on head classes. Our code and models are available on http://bit.ly/LTVRR.