Related papers: Generalizing MLPs With Dropouts, Batch Normalizati…

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this…

In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) has achieved excellent performance in numerous computer…

Polarization image fusion combines S0 and DOLP images to reveal surface roughness and material properties through complementary texture features, which has important applications in camouflage recognition, tissue pathology analysis, surface…

A morphological perceptron is a multilayer feedforward neural network in which neurons perform elementary operations from mathematical morphology. For multiclass classification tasks, a morphological perceptron with a competitive layer…

In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the MLPs are able to represent complex scenes with unprecedented…

Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model in the traditional Multilayer Perceptron (MLP) and this model can mimic the synaptic connections of the biological neurons that have nonlinear…

Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However,…

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…

In this paper, we present a MLP-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications. In designing Triangular Mixer, we simplify the cross-token operation in MLP as the…

Assessing the performance of systems to classify Multi-Party Conversations (MPC) is challenging due to the interconnection between linguistic and structural characteristics of conversations. Conventional evaluation methods often overlook…

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability. In a trainability study, one aims to discern what…

All simulation approaches eventually face limits in computational scalability when applied to large spatiotemporal domains. This challenge becomes especially apparent in molecular-level particle simulations, where high spatial and temporal…

Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteristics from logged user behavior data for accurate…

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through…

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…

Time series forecasters are widely used across various domains. Among them, MLP (multi-layer perceptron)-based forecasters have been proven to be more robust to noise compared to Transformer-based forecasters. However, MLP struggles to…

In recent studies, neural message passing has proved to be an effective way to design graph neural networks (GNNs), which have achieved state-of-the-art performance in many graph-based tasks. However, current neural-message passing…

We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron (MLP), for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g.,…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…