Search for: All records

Is intelligence realized by connectionist or classicist? While connectionist approaches have achieved superhuman performance, there has been growing evidence that such task-specific superiority is particularly fragile in systematic generalization. This observation lies in the central debate between connectionist and classicist, wherein the latter continually advocates an algebraic treatment in cognitive architectures. In this work, we follow the classicist’s call and propose a hybrid approach to improve systematic generalization in reasoning. Specifically, we showcase a prototype with algebraic representation for the abstract spatial-temporal reasoning task of Raven’s Progressive Matrices (RPM) and present the ALgebra-Aware Neuro-Semi-Symbolic (ALANS) learner. The ALANS learner is motivated by abstract algebra and the representation theory. It consists of a neural visual perception frontend and an algebraic abstract reasoning backend: the frontend summarizes the visual information from object-based representation, while the backend transforms it into an algebraic structure and induces the hidden operator on the fly. The induced operator is later executed to predict the answer’s representation, and the choice most similar to the prediction is selected as the solution. Extensive experiments show that by incorporating an algebraic treatment, the ALANS learner outperforms various pure connectionist models in domains requiring systematic generalization. We further show the generative naturemore »of the learned algebraic representation; it can be decoded by isomorphism to generate an answer.« less

Abstract The relationship between extreme precipitation intensity and temperature has been comprehensively studied over different regions worldwide. However, the effect of temperature on the spatiotemporal organization of precipitation, which can have a significant impact on precipitation intensity, has not been adequately studied or understood. In this study, we propose a novel approach to quantifying the spatial and temporal concentration of precipitation at the event level and study how the concentration varies with temperature. The results based on rain gauge data from 843 stations in the Ganzhou county, a humid region in south China, show that rain events tend to be more concentrated both temporally and spatially at higher temperature, and this increase in concentration qualitatively holds for events of different precipitation amounts and durations. The effects of temperature on precipitation organization in space and in time differ at high temperatures. The temporal concentration increases with temperature up to a threshold (approximately 24°C) beyond which it plateaus, whereas the spatial concentration keeps rising with temperature. More concentrated precipitation, in addition to a projected increase of extreme precipitation, would intensify flooding in a warming world, causing more detrimental effects.

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built upon it have made interesting attempts aiming at the interpretability of text modeling. However, latent space EBMs also inherit some flaws from EBMs in data space; the degenerate MCMC sampling quality in practice can lead to poor generation quality and instability in training, especially on data with complex latent structures. Inspired by the recent efforts that leverage diffusion recovery likelihood learning as a cure for the sampling issue, we introduce a novel symbiosis between the diffusion models and latent space EBMs in a variational learning framework, coined as the latent diffusion energy-based model. We develop a geometric clustering-based regularization jointly with the information bottleneck to further improve the quality of the learned latent space. Experiments on several challenging tasks demonstrate the superior performance of our model on interpretable text modeling over strong counterparts.

Neural networks are often represented as graphs of connections between neurons. However, despite their wide use, there is currently little understanding of the relationship between the graph structure of the neural network and its predictive performance. Here we systematically investigate how does the graph structure of neural networks affect their predictive performance. To this end, we develop a novel graph-based representation of neural networks called relational graph, where layers of neural network computation correspond to rounds of message exchange along the graph structure. Using this representation we show that: (1) a “sweet spot” of relational graphs leads to neural networks with significantly improved predictive performance; (2) neural network’s performance is approximately a smooth function of the clustering coefficient and average path length of its relational graph; (3) our findings are consistent across many different tasks and datasets; (4) the sweet spot can be identified efficiently; (5) topperforming neural networks have graph structure surprisingly similar to those of real biological neural networks. Our work opens new directions for the design of neural architectures and the understanding on neural networks in general.

Abstract The U.S. Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) program User Facility produces ground-based long-term continuous unique measurements for atmospheric state, precipitation, turbulent fluxes, radiation, aerosol, cloud, and the land surface, which are collected at multiple sites. These comprehensive datasets have been widely used to calibrate climate models and are proven to be invaluable for climate model development and improvement. This article introduces an evaluation package to facilitate the use of ground-based ARM measurements in climate model evaluation. The ARM data-oriented metrics and diagnostics package (ARM-DIAGS) includes both ARM observational datasets and a Python-based analysis toolkit for computation and visualization. The observational datasets are compiled from multiple ARM data products and specifically tailored for use in climate model evaluation. In addition, ARM-DIAGS also includes simulation data from models participating the Coupled Model Intercomparison Project (CMIP), which will allow climate-modeling groups to compare a new, candidate version of their model to existing CMIP models. The analysis toolkit is designed to make the metrics and diagnostics quickly available to the model developers.

Last year, the report of Room-Temperature Superconductivity in high-pressure carbonaceous sulfur hydride marked a major milestone in the history of physics: one of the holy grails of condensed matter research was reached after more than one century of continuing efforts. This long path started with Neil Ashcroft’s and Vitaly Ginzburg’s visionary insights on high-temperature superconductivity in metallic hydrogen in the 60’s and 70’s, and has led to the current hydride fever, following the report of high-Tc high-pressure superconductivity in H3S in 2014. This Roadmap collects selected contributions from many of the main actors in this exciting chapter of condensed matter history. Key for the rapid progress of this field has been a new course for materials discovery, where experimental and theoretical discoveries proceed hand in hand. The aim of this Roadmap is not only to offer a snapshot of the current status of superconductor materials research, but also to define the theoretical and experimental obstacles that must be overcome for us to realize fully exploitable room temperature superconductors, and foresee future strategies and research directions. This means improving synthesis techniques, extending first-principles methods for superconductors and structural search algorithms for crystal structure predictions, but also identifying new approaches to materialmore »discovery based on artificial intelligence.« less