An ongoing study at Cortical Labs in Australia demonstrates how I am Cultured neurons To manage Learn to play pong Faster than Artificial intelligence, Despite lower results than these in the long run. Lessons learned, brain tissue cells cultured in petri foods, through a system called "DishBrain", create a kind of autonomous brain mass that puts human stem cells on top of the microelectronic matrix and builds brain cells. These cells receive electrical inputs through electrodes and were tested in the style of the popular Atari game in the early 70s. Research has shown that these brain cells learn to play and play much faster than an artificial intelligence system: based on the data, cultured neurons learn to react and "play". However, it is also true that artificial intelligence is more accurate than brain cells.

This is an up-to-date introduction to, and overview of, marginal likelihood computation for model selection and hypothesis testing. Computing normalizing constants of probability models (or ratio of constants) is a fundamental issue in many applications in statistics, applied mathematics, signal processing and machine learning. This article provides a comprehensive study of the state-of-the-art of the topic. We highlight limitations, benefits, connections and differences among the different techniques. Problems and possible solutions with the use of improper priors are also described. Some of the most relevant methodologies are compared through theoretical comparisons and numerical experiments.

Machine learning can be enhanced through the integration of external knowledge. This method, called knowledge informed machine learning, is also applicable within the field of Prognostics and Health Management (PHM). In this paper, the various methods of knowledge informed machine learning, from a PHM context, are reviewed with the goal of helping the reader understand the domain. In addition, a knowledge informed machine learning technique is demonstrated, using the common IMS and PRONOSTIA bearing data sets, for remaining useful life (RUL) prediction. Specifically, knowledge is garnered from the field of reliability engineering which is represented through the Weibull distribution. The knowledge is then integrated into a neural network through a novel Weibull-based loss function. A thorough statistical analysis of the Weibull-based loss function is conducted, demonstrating the effectiveness of the method on the PRONOSTIA data set. However, the Weibull-based loss function is less effective on the IMS data set. The results, shortcomings, and benefits of the approach are discussed in length. Finally, all the code is publicly available for the benefit of other researchers.

Fake news spread widely on social media in various domains, which lead to real-world threats in many aspects like politics, disasters, and finance. Most existing approaches focus on single-domain fake news detection (SFND), which leads to unsatisfying performance when these methods are applied to multi-domain fake news detection. As an emerging field, multi-domain fake news detection (MFND) is increasingly attracting attention. However, data distributions, such as word frequency and propagation patterns, vary from domain to domain, namely domain shift. Facing the challenge of serious domain shift, existing fake news detection techniques perform poorly for multi-domain scenarios. Therefore, it is demanding to design a specialized model for MFND. In this paper, we first design a benchmark of fake news dataset for MFND with domain label annotated, namely Weibo21, which consists of 4,488 fake news and 4,640 real news from 9 different domains. We further propose an effective Multi-domain Fake News Detection Model (MDFEND) by utilizing a domain gate to aggregate multiple representations extracted by a mixture of experts. The experiments show that MDFEND can significantly improve the performance of multi-domain fake news detection. Our dataset and code are available at https://github.com/kennqiang/MDFEND-Weibo21.

We demonstrate that a neural network pre-trained on text and fine-tuned on code solves Mathematics problems by program synthesis. We turn questions into programming tasks, automatically generate programs, and then execute them, perfectly solving university-level problems from MIT's large Mathematics courses (Single Variable Calculus 18.01, Multivariable Calculus 18.02, Differential Equations 18.03, Introduction to Probability and Statistics 18.05, Linear Algebra 18.06, and Mathematics for Computer Science 6.042), Columbia University's COMS3251 Computational Linear Algebra course, as well as questions from a MATH dataset (on Prealgebra, Algebra, Counting and Probability, Number Theory, and Precalculus), the latest benchmark of advanced mathematics problems specifically designed to assess mathematical reasoning. We explore prompt generation methods that enable Transformers to generate question solving programs for these subjects, including solutions with plots. We generate correct answers for a random sample of questions in each topic. We quantify the gap between the original and transformed questions and perform a survey to evaluate the quality and difficulty of generated questions. This is the first work to automatically solve, grade, and generate university-level Mathematics course questions at scale. This represents a milestone for higher education.

Recently, graph neural networks have become a hot topic in machine learning community. This paper presents a Scopus based bibliometric overview of the GNNs research since 2004, when GNN papers were first published. The study aims to evaluate GNN research trend, both quantitatively and qualitatively. We provide the trend of research, distribution of subjects, active and influential authors and institutions, sources of publications, most cited documents, and hot topics. Our investigations reveal that the most frequent subject categories in this field are computer science, engineering, telecommunications, linguistics, operations research and management science, information science and library science, business and economics, automation and control systems, robotics, and social sciences. In addition, the most active source of GNN publications is Lecture Notes in Computer Science. The most prolific or impactful institutions are found in the United States, China, and Canada. We also provide must read papers and future directions. Finally, the application of graph convolutional networks and attention mechanism are now among hot topics of GNN research.

People's decisions about how to allocate their limited computational resources are essential to human intelligence. An important component of this metacognitive ability is deciding whether to continue thinking about what to do and move on to the next decision. Here, we show that people acquire this ability through learning and reverse-engineer the underlying learning mechanisms. Using a process-tracing paradigm that externalises human planning, we find that people quickly adapt how much planning they perform to the cost and benefit of planning. To discover the underlying metacognitive learning mechanisms we augmented a set of reinforcement learning models with metacognitive features and performed Bayesian model selection. Our results suggest that the metacognitive ability to adjust the amount of planning might be learned through a policy-gradient mechanism that is guided by metacognitive pseudo-rewards that communicate the value of planning.

Instead of the traditional Knowledge Graph Embedding (KGE) represents entities and Negative Sampling, we design a new loss function based on relations of knowledge graphs (KGs) in the semantic vector space, query sampling that can balance two important training targets, and has shown great potential in automatic KG completion and Alignment and Uniformity. Furthermore, we analyze the hardnessaware knowledge-driven tasks [15, 16, 31, 33]. Given a query having an ability of recent low-dimensional hyperbolic models and entity and the relation of a triple, a typical KGE model learns propose a lightweight hardness-aware activation mechanism, which embedding vectors by predicting the missing entity from the can help the KGE models focus on hard instances and speed up whole entity set [30]. However, the existing KGE models have convergence. The experimental results show that in the limited limited practicality in real-world applications [19, 23]. To improve training time, HaLE can effectively improve the performance and the prediction accuracy, recent KGE models utilize complicated training speed of KGE models on five commonly-used datasets. The computational structures and high-dimensional vectors up to 500 or HaLE-trained models can obtain a high prediction accuracy after even 1,000 dimensions [7, 12, 22]. Training such high-dimensional training few minutes and are competitive compared to the state-ofthe-art models demands prohibitive training costs and storage space, yet models in both low-and high-dimensional conditions.

In this paper, we introduce zero-shot cost models which enable learned cost estimation that generalizes to unseen databases. In contrast to state-of-the-art workload-driven approaches which require to execute a large set of training queries on every new database, zero-shot cost models thus allow to instantiate a learned cost model out-of-the-box without expensive training data collection. To enable such zero-shot cost models, we suggest a new learning paradigm based on pre-trained cost models. As core contributions to support the transfer of such a pre-trained cost model to unseen databases, we introduce a new model architecture and representation technique for encoding query workloads as input to those models. As we will show in our evaluation, zero-shot cost estimation can provide more accurate cost estimates than state-of-the-art models for a wide range of (real-world) databases without requiring any query executions on unseen databases. Furthermore, we show that zero-shot cost models can be used in a few-shot mode that further improves their quality by retraining them just with a small number of additional training queries on the unseen database.

According to a report from Apollo Hospitals, there are only about 10,000 trained radiologists for the current population of India, and AI-based radiology reporting could be a saviour to address the shortage of radiologists. Synapsica, an AI-based radiology reporting start-up, has been using AI-powered technology that automates several aspects of radiology workflow, improves the quality of reports, and increases transparency between patients and doctors. Meenakshi Singh, Co-Founder and CEO of Synapsica, saw the effect of the shortage of radiologists in her hometown in UP and decided to use her AI chops to find a faster and more efficient method to reduce the workload of doctors and radiologists, to help patients get their diagnoses sooner. How is AI used in radiology workflow? Explaining how AI is used in radiology workflow, Meenakshi said, "Once a patient scan is taken, and the information reaches our secure cloud server, the AI engine automatically creates biomarkers of pathologies that are shared with the reporting radiologist in a viewer that presents the patient's scan. A layer of NLP on top of AI-generated bio-markers also pre-fills radiology reports with relevant clinical findings that can be edited by the radiologist, saving typing time. The AI engine also generates reporting instructions that automate tasks normally performed by back-office support personnel."