Related papers: climt-paraformer: Stable Emulation of Convective P…

The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes.…

Deep learning approaches have demonstrated success in modeling analog audio effects. Nevertheless, challenges remain in modeling more complex effects that involve time-varying nonlinear elements, such as dynamic range compressors. Existing…

Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to tabular data modelling. However, many of these applications are…

The recurrent neural network and its variants have shown great success in processing sequences in recent years. However, this deep neural network has not aroused much attention in anomaly detection through predictively process monitoring.…

Modeling boiling (an inherently chaotic, multiphase process central to energy and thermal systems) remains a significant challenge for neural PDE surrogates. Existing models require future input (e.g., bubble positions) during inference…

Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online…

Persistent Memory (PMEM), also known as Non-Volatile Memory (NVM), can deliver higher density and lower cost per bit when compared with DRAM. Its main drawback is that it is typically slower than DRAM. On the other hand, DRAM has…

Continuous-Time Recurrent Neural Networks (CTRNNs) have been widely used for their capacity to model complex temporal behaviour. However, their internal dynamics often remain difficult to interpret. In this paper, we propose a new class of…

Representing and quantifying uncertainty in physical parameterisations is a central challenge in weather and climate modelling, and approaches are often developed separately for different timescales. Here, we introduce a unified framework…

We study the approximation properties of convolutional architectures applied to time series modelling, which can be formulated mathematically as a functional approximation problem. In the recurrent setting, recent results reveal an…

Modern convolutional neural networks (CNNs) organize computation as a discrete stack of layers whose parameters are independently stored and learned, with the number of layers fixed as an architectural hyperparameter. In this work, we…

Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance…

Graphs are an essential part of many machine learning problems such as analysis of parse trees, social networks, knowledge graphs, transportation systems, and molecular structures. Applying machine learning in these areas typically involves…

Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the proposed approach comes with…

Machine-learning-based parameterizations (i.e. representation of sub-grid processes) of global climate models or turbulent simulations have recently been proposed as a powerful alternative to physical, but empirical, representations,…

Convolutional neural networks (CNNs) can potentially provide powerful tools for classifying and identifying patterns in climate and environmental data. However, because of the inherent complexities of such data, which are often…

The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in…

Current climate models often struggle with accuracy because they lack sufficient resolution, a limitation caused by computational constraints. This reduces the precision of weather forecasts and long-term climate predictions. To address…

Global environmental challenges and rising energy demands have led to extensive exploration of wind energy technologies. Accurate wind speed forecasting (WSF) is crucial for optimizing wind energy capture and ensuring system stability.…

Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task…