Experimental design in field robotics is an adaptive human-in-the-loop decision-making process in which an experimenter learns about system performance and limitations through interactions with a robot in the form of constructed experiments. This can be challenging because of system complexity, the need to operate in unstructured environments, and the competing objectives of maximizing information gain while simultaneously minimizing experimental costs. Based on the successes in other domains, we propose the use of a Decision Support System (DSS) to amplify the human's decision-making abilities, overcome their inherent shortcomings, and enable principled decision-making in field experiments. In this work, we propose common terminology and a six-stage taxonomy of DSSs specifically for adaptive experimental design of more informative tests and reduced experimental costs. We construct and present our taxonomy using examples and trends from DSS literature, including works involving artificial intelligence and Intelligent DSSs. Finally, we identify critical technical gaps and opportunities for future research to direct the scientific community in the pursuit of next-generation DSSs for experimental design.

Embedded topic models are able to learn interpretable topics even with large and heavy-tailed vocabularies. However, they generally hold the Euclidean embedding space assumption, leading to a basic limitation in capturing hierarchical relations. To this end, we present a novel framework that introduces hyperbolic embeddings to represent words and topics. With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics. Furthermore, due to the superiority of hyperbolic geometry in representing hierarchical data, tree-structure knowledge can also be naturally injected to guide the learning of a topic hierarchy. Therefore, we further develop a regularization term based on the idea of contrastive learning to inject prior structural knowledge efficiently. Experiments on both topic taxonomy discovery and document representation demonstrate that the proposed framework achieves improved performance against existing embedded topic models.

With the global population expected to exceed 9 billion by 2050, food security is one of the most important objectives of our time. The agricultural economy employs 65–70 per cent of Africa's labour force and typically accounts for 30–40 per cent of GDP according to the World Bank. With the population in Africa estimated to reach about 2.6 billion by 2050, it is now important that agriculture and food systems be reviewed in order to find innovative approaches at improving food production and utilisation to enhance food security. Being a high-priority sector for the African economy, agriculture, broadly comprising farming and forestry, livestock (milk, eggs and meat) and fisheries, is on the verge of massive transformation with a greater focus on technology integration. Considering the spectrum of the sector, agriculture is still mired with challenges spread across the value chain and needs better optimisation of operations.

Aliens, astronauts, time travel--you name it, there's a dazzling sci-fi film about it. That makes compiling a list of the best sci-fi nearly impossible. It's almost impossible to know where to start--or where to stop. To understand where sci-fi films came from, you need to head back to the dawn of the cinema age. Right at the beginning, Metropolis, released in 1927, used groundbreaking visuals to create a reference point for all future urban dystopias--it's no fluke, for example, that the aesthetic of Blade Runner bears more than a passing resemblance to Fritz Lang's prophetic city hellscape. Then along came War of the Worlds (1953), a gripping tale of alien invasion adapted from H. G. Wells' classic novel. In 1964, Dr. Strangelove did more than most films before or since to ossify the fear of a nuclear holocaust. Below is WIRED's ever-evolving selection of the sci-fi movies everyone should watch, from the obscure to the hugely influential. You may also enjoy our guides to the best sci-fi books of all time and the best space movies. This content can also be viewed on the site it originates from. When Alfonso Cuarón wrote the screenplay for Gravity, he wasn't setting out to make a film about space itself. Rather, he was interested in exploring the concepts of adversity and human resilience, with space as a secondary background. But it was hard for audiences to not be wowed by the visuals in this Oscar-winning film about two scientists (George Clooney and Sandra Bullock) who find themselves stranded in space, and what they must endure in order to get safely back to Earth.

CSE graduate student Yu-Wei Chao has been selected to receive a 2016 Google PhD Fellowship to support his work in the area of computer vision and machine learning. This year, Google awarded 39 fellowships to top PhD students in the US and Canada who are doing exceptional work in computer science, related disciplines, or promising research areas. Yu-Wei is a third year PhD student working with Prof. Jia Deng. His research focuses on computer vision and machine learning. He was awarded the Google PhD Fellowship based on his recent work on large-scale visual recognition of human actions.

Google on Tuesday announced a broad swath of updates to its cloud offerings, aiming to capitalize on its strength in artificial intelligence to gain market share from rivals. The new services--announced at Google's Next '22 event--include Vertex AI Vision, which is designed to make it easier to use AI technology such as image recognition. There's also an AI-based service called Translation Hub that translates documents in 135 languages, the Alphabet Inc.-owned company said. Google is beefing up its cloud infrastructure as well, relying on a fourth-generation version of Intel Corp.'s Xeon Scalable processor and Google's custom Intel chip. The company unveiled a new C3 machine series that's powered by the chips, as well as an updated Tensor processing unit that helps accelerate AI functions.

Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as the source CSKB for training is of a relatively smaller scale (1M) while the whole candidate space for population is way larger (200M). We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from. The teacher can be a generative model rather than restricted to discriminative models as previous works. In addition, we design a new filtering procedure for pseudo labels based on influence function and the student model's prediction to further improve the performance. The framework can improve the backbone model KG-BERT (RoBERTa-large) by 3.3 points on the overall performance and especially, 5.3 points on the out-of-domain performance, and achieves the state-of-the-art. Codes and data are available at https://github.com/HKUST-KnowComp/PseudoReasoner.

Solar energy is one of the most dependable renewable energy technologies, as it is feasible almost everywhere globally. However, improving the efficiency of a solar PV system remains a significant challenge. To enhance the robustness of the solar system, this paper proposes a trained convolutional neural network (CNN) based fault detection scheme to divide the images of photovoltaic modules. For binary classification, the algorithm classifies the input images of PV cells into two categories (i.e. faulty or normal). To further assess the network's capability, the defective PV cells are organized into shadowy, cracked, or dusty cells, and the model is utilized for multiple classifications. The success rate for the proposed CNN model is 91.1% for binary classification and 88.6% for multi-classification. Thus, the proposed trained CNN model remarkably outperforms the CNN model presented in a previous study which used the same datasets. The proposed CNN-based fault detection model is straightforward, simple and effective and could be applied in the fault detection of solar panel.

Knowledge graph (KG) embedding techniques use structured relationships between entities to learn low-dimensional representations of entities and relations. The traditional KG embedding techniques (such as TransE and DistMult) estimate these embeddings via simple models developed over observed KG triplets. These approaches differ in their triplet scoring loss functions. As these models only use the observed triplets to estimate the embeddings, they are prone to suffer through data sparsity that usually occurs in the real-world knowledge graphs, i.e., the lack of enough triplets per entity. To settle this issue, we propose an efficient method to augment the number of triplets to address the problem of data sparsity. We use random walks to create additional triplets, such that the relations carried by these introduced triplets entail the metapath induced by the random walks. We also provide approaches to accurately and efficiently filter out informative metapaths from the possible set of metapaths, induced by the random walks. The proposed approaches are model-agnostic, and the augmented training dataset can be used with any KG embedding approach out of the box. Experimental results obtained on the benchmark datasets show the advantages of the proposed approach.

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical to rumor detection in practice. To discover subtle vulnerabilities, we design a powerful attacking algorithm to camouflage rumors in social networks based on reinforcement learning that can interact with and attack any black-box detectors. The environment has exponentially large state spaces, high-order graph dependencies, and delayed noisy rewards, making the state-of-the-art end-to-end approaches difficult to learn features as large learning costs and expressive limitation of graph deep models. Instead, we design domain-specific features to avoid learning features and produce interpretable attack policies. To further speed up policy optimization, we devise: (i) a credit assignment method that decomposes delayed rewards to atomic attacking actions proportional to the their camouflage effects on target rumors; (ii) a time-dependent control variate to reduce reward variance due to large graphs and many attacking steps, supported by the reward variance analysis and a Bayesian analysis of the prediction distribution. On three real world datasets of rumor detection tasks, we demonstrate: (i) the effectiveness of the learned attacking policy compared to rule-based attacks and current end-to-end approaches; (ii) the usefulness of the proposed credit assignment strategy and variance reduction components; (iii) the interpretability of the policy when generating strong attacks via the case study.