相关论文: FAN: Fourier Analysis Networks

Long-term time series forecasting plays an important role in various real-world scenarios. Recent deep learning methods for long-term series forecasting tend to capture the intricate patterns of time series by decomposition-based or…

Quantum neural networks represent a new machine learning paradigm that has recently attracted much attention due to its potential promise. Under certain conditions, these models approximate the distribution of their dataset with a truncated…

In the field of systems biology, differential equations are commonly used to model biological systems, but solving them for large-scale and complex systems can be computationally expensive. Recently, the integration of machine learning and…

Since clicks usually contain heavy noise, increasing research efforts have been devoted to modeling implicit negative user behaviors (i.e., non-clicks). However, they either rely on explicit negative user behaviors (e.g., dislikes) or…

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly…

Deep Reinforcement Learning (DRL) has become a powerful tool for developing control policies in queueing networks, but the common use of Multi-layer Perceptron (MLP) neural networks in these applications has significant drawbacks. MLP…

Learning to solve the Alternating Current Optimal Power Flow (AC-OPF) problem by neural networks (NNs) is a promising approach in real-time applications. Existing methods to ensure the physical feasibility of NN outputs embed a power flow…

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach…

The Fourier transform, an explicit decomposition method for visual signals, has been employed to explain the out-of-distribution generalization behaviors of Deep Neural Networks (DNNs). Previous studies indicate that the amplitude spectrum…

This paper answers a fundamental question in artificial neural network (ANN) design: We do not need to build ANNs layer-by-layer sequentially to guarantee the Directed Acyclic Graph (DAG) property. Drawing inspiration from biological…

In order to make Internet connections ubiquitous and autonomous in our daily lives, maximizing the utilization of radio resources and social information is one of the major research topics in future mobile communication technologies. Fog…

Neural networks are often utilised in critical domain applications (e.g. self-driving cars, financial markets, and aerospace engineering), even though they exhibit overconfident predictions for ambiguous inputs. This deficiency demonstrates…

Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based models, often…

The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only capable of representing the addition operator, the…

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased…

\textit{Graph neural networks} (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types…

The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series-based multi-dataset models…

Recent work in scientific machine learning has developed so-called physics-informed neural network (PINN) models. The typical approach is to incorporate physical domain knowledge as soft constraints on an empirical loss function and use…

Recent work has empirically shown that deep neural networks latch on to the Fourier statistics of training data and show increased sensitivity to Fourier-basis directions in the input. Understanding and modifying this Fourier-sensitivity of…

We build upon the functional object-oriented network (FOON), a structured knowledge representation which is constructed from observations of human activities and manipulations. A FOON can be used for representing object-motion affordances.…