To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.
Relational databases have been around for a long time and spatial databases have exploited this feature for close to two decades. The recent past has seen the development of NoSQL non-relational databases, which are now being adopted for spatial object storage and handling, too. While SQL databases face scalability and agility challenges and fail to take the advantage of the cheap memory and processing power available these days, NoSQL databases can handle the rise in the data storage and frequency at which it is accessed and processed - which are essential features needed in geospatial scenarios, which do not deal with a fixed schema(geometry) and fixed data size. This paper attempts to evaluate the performance of an existing NoSQL database 'MongoDB' with its inbuilt spatial functions with that of a SQL database with spatial extension 'PostGIS' for two problems – spatial and aggregate queries, across a range of datasets, with varying features counts. All the data in the analysis was processed In-memory and no secondary memory was used. Initial results suggest that MongoDB performs better by an average factor of 10x-25x which increases exponentially as the data size increases in both indexed and non-indexed operations. Given these results, NoSQL databases may be better suited for simultaneous multiple-user query systems including Web-GIS and mobile-GIS. Further studies are required to understand the full potential of NoSQL databases across various geometries and spatial query types.
We present a new technology-based paradigm to support embodied mathematics educational games, using wearable devices in the form of SmartPhones and SmartWatches for math learning, for full classes of students in formal in-school education settings. The Wearable Learning Games Engine is web based infrastructure that enables students to carry one mobile device per child, as they embark on math team-based activities that require physical engagement with the environment. These Wearable Tutors serve as guides and assistants while students manipulate, measure, estimate, discern, discard and find mathematical objects that satisfy specified constraints. Multiplayer math games that use this infrastructure have yielded both cognitive and affective benefits. Beyond math game play, the Wearable Games Engine Authoring Tool enables students to create games themselves for other students to play; in this process, students engage in computational thinking and learn about finite-state machines. We present the infrastructure, games, and results for a series of experiments on both game play and game creation.
Fire hazard is a condition that has potentially catastrophic consequences. Artificial intelligence, through Computer Vision, in combination with UAVs has assisted dramatically to identify this risk and avoid it in a timely manner. This work is a literature review on UAVs using Computer Vision in order to detect fire. The research was conducted for the last decade in order to record the types of UAVs, the hardware and software used and the proposed datasets. The scientific research was executed through the Scopus database. The research showed that multi-copters were the most common type of vehicle and that the combination of RGB with a thermal camera was part of most applications. In addition, the trend in the use of Convolutional Neural Networks (CNNs) is increasing. In the last decade, many applications and a wide variety of hardware and methods have been implemented and studied. Many efforts have been made to effectively avoid the risk of fire. The fact that state-of-the-art methodologies continue to be researched, leads to the conclusion that the need for a more effective solution continues to arouse interest.
Left-wing authoritarianism remains far less understood than right-wing authoritarianism. We contribute to the literature on the former, which typically relies on surveys, using a new social media analytics approach. We use a list of 60 terms to provide an exploratory sketch of the outlines of a political ideology (tribal equalitarianism) with origins in 19th and 20th century social philosophy. We then use analyses of the English Corpus of Google Books (over 8 million books) and scraped unique tweets from Twitter (n = 202,852) to conduct a series of investigations to discern the extent to which this ideology is cohesive amongst the public, reveals signatures of authoritarianism and has been growing in popularity. Though exploratory, our results provide some evidence of left-wing authoritarianism in two forms (1) a uniquely conservative moral signature amongst ostensible liberals using measures from Moral Foundations Theory and (2) a substantial prevalence of anger, relative to anxiety or sadness. In general, results indicate that this worldview is growing in popularity, is increasingly cohesive, and shows signatures of authoritarianism.
We present the new Water Ecosystems Tool (WET), a workflow implemented (as a plugin) in QGIS, for application and evaluation of aquatic ecosystem models. WET provides a Graphical User Interface (GUI) for the coupled one-dimensional hydrodynamic-ecosystem model GOTM-FABM-PCLake. WET is unique as it enables a standardized and easy-to-use workflow for an otherwise complex model application and is readily applicable to any individual lake and reservoir in the world. WET integrates a platform for model experimentation through scenario simulations – currently encompassing changes in climate and nutrient loads. WET also includes a link to the SWAT (Soil & Water Assessment Tool) watershed model, which can be used to simulate how land use changes affect aquatic ecosystems. The tool is open source and may therefore be readily expanded and adapted for additional model experimentations.
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d). This nested system of two flows, where the parameter-flow is constrained to lie on the compact manifold, provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem which is intrinsically related to training deep neural network architectures such as Neural ODEs. Consequently, it leads to better downstream models, as we show on the example of training reinforcement learning policies with evolution strategies, and in the supervised learning setting, by comparing with previous SOTA baselines. We provide strong convergence results for our proposed mechanism that are independent of the depth of the network, supporting our empirical studies. Our results show an intriguing connection between the theory of deep neural networks and the field of matrix flows on compact manifolds.
We present a novel view on principal component analysis (PCA) as a competitive game in which each approximate eigenvector is controlled by a player whose goal is to maximize their own utility function. We analyze the properties of this PCA game and the behavior of its gradient based updates. The resulting algorithm -- which combines elements from Oja's rule with a generalized Gram-Schmidt orthogonalization -- is naturally decentralized and hence parallelizable through message passing. We demonstrate the scalability of the algorithm with experiments on large image datasets and neural network activations. We discuss how this new view of PCA as a differentiable game can lead to further algorithmic developments and insights.