Related papers: Supervised learning with artificial hydrocarbon ne…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous…

While software implementations of neural networks have driven significant advances in computation, the von Neumann architecture imposes fundamental limitations on speed and energy efficiency. Neuromorphic networks, with structures inspired…

Human action recognition (HAR) is a high-level and significant research area in computer vision due to its ubiquitous applications. The main limitations of the current HAR models are their complex structures and lengthy training time. In…

Attention mechanisms have been boosting the performance of deep learning models on a wide range of applications, ranging from speech understanding to program induction. However, despite experiments from psychology which suggest that…

With the success of self-supervised learning, multimodal foundation models have rapidly adapted a wide range of downstream tasks driven by vision and language (VL) pretraining. State-of-the-art methods achieve impressive performance by…

Heterogeneous ultra-dense network (H-UDN) is envisioned as a promising solution to sustain the explosive mobile traffic demand through network densification. By placing access points, processors, and storage units as close as possible to…

Optimizing the operation of heating, ventilation, and air-conditioning (HVAC) systems is a challenging task, requiring the modeling of complex nonlinear relationships among HVAC load, indoor temperatures, and outdoor environments. This…

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN…

We present E NERGY N ET , a new framework for analyzing and building artificial neural network architectures. Our approach adaptively learns the structure of the networks in an unsupervised manner. The methodology is based upon the…

The in silico exploration of chemical, physical and biological systems requires accurate and efficient energy functions to follow their nuclear dynamics at a molecular and atomistic level. Recently, machine learning tools gained a lot of…

Modeling of conservative systems with neural networks is an area of active research. A popular approach is to use Hamiltonian neural networks (HNNs) which rely on the assumptions that a conservative system is described with Hamilton's…

Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems. The models combine experts that model relevant distributions at…

Autonomous vehicle (AV) navigation in the presence of Human-driven vehicles (HVs) is challenging, as HVs continuously update their policies in response to AVs. In order to navigate safely in the presence of complex AV-HV social…

Graph neural networks (GNN) has been successfully applied to operate on the graph-structured data. Given a specific scenario, rich human expertise and tremendous laborious trials are usually required to identify a suitable GNN architecture.…

Recent promising effort for spectral reconstruction (SR) focuses on learning a complicated mapping through using a deeper and wider convolutional neural networks (CNNs). Nevertheless, most CNN-based SR algorithms neglect to explore the…

Multi-Agent Reinforcement Learning is widely used for multi-robot coordination, where simple graphs typically model pairwise interactions. However, such representations fail to capture higher-order collaborations, limiting effectiveness in…

Since Convolutional Neural Networks (ConvNets) are able to simultaneously learn features and classifiers to discriminate different categories of activities, recent works have employed ConvNets approaches to perform human activity…

Deep hashing has shown to be a complexity-efficient solution for the Approximate Nearest Neighbor search problem in high dimensional space. Many methods usually build the loss function from pairwise or triplet data points to capture the…

Recommender systems play a crucial role in alleviating information overload by providing personalized recommendations tailored to users' preferences and interests. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach…