Shuai Li

Further Investigations on Noise-Tolerant Zeroing Neural Network for Time-Varying Quadratic Programming with Robotic Applications

2017

Recently, a modified zeroing neural network (MZNN) model has been presented for solving quadratic programming problems, which is of noise-tolerant ability. In this paper, we conduct further investigations on such a model and then present …

The Gambler's Problem and Beyond

2019 · arXiv (Cornell University)

We analyze the Gambler's problem, a simple reinforcement learning problem where the gambler has the chance to double or lose the bets until the target is reached. This is an early example introduced in the …

Towards Understanding the Regularization of Adversarial Robustness on\n Neural Networks

2020 · arXiv (Cornell University)

The problem of adversarial examples has shown that modern Neural Network (NN)\nmodels could be rather fragile. Among the more established techniques to solve\nthe problem, one is to require the model to be {\\it $\\epsilon$-adversarially\nrobust} (AR); …

Network computer security and protection measures based on information security risk in cloud computing environment

2021

Cloud computing based on Internet is considered as the development direction of Internet nowadays, which has aroused widespread concern in recent years. How to build a secure cloud computing environment has become one of the …

Forms and Results of Zhang Neuronet of Reciprocal Kind Dealing with Time-Variant Overdetermined System of Linear Equations

2022

In order to deal with time-variant overdetermined system of linear equations (TVOSLE), a new approach termed Zhang neuronet of reciprocal kind (ZNRK) is proposed and reformulated. As developed from the continuous-time Zhang neuronet (CTZN), the …

Graph Neural Networks based Recommendation Methods in Different Scenarios: A Survey

2022

Recommendation system is one of the most important service applications in the world, and graph neural network is currently the most popular research direction in the field of recommendation system. In this survey, we conduct …

Soft Sensor Model for Billet Temperature in Multiple Heating Furnaces Based on Transfer Learning

2023 · IEEE Transactions on Instrumentation and Measurement

Billet heating temperature directly affects the quality of the billet, but the existing technology cannot measure the billet surface temperature. Therefore, we accurately predict the temperature of the furnace by a soft sensor to approximate …

Chaotic Time Series Prediction of Echo State Network Based on Memristor

2024

In this paper, we proposed a new echo state network (ESN) model, namely echo state network based on memristor (memristor-ESN). It improve the memory function of the reservoir and the prediction performance of the ESN. …

Enhancing Electric Power Industry Image-Text Matching with Image Properties

2024

The electric power industry has many valuable images containing meaningful information, such as on-site physical and technical schematic images, which can guide employees in operation and learning. However, these images sleep in documents because they …

Proxy Prompt: Endowing SAM and SAM 2 with Auto-Interactive-Prompt for Medical Segmentation

2025 · arXiv (Cornell University)

In this paper, we aim to address the unmet demand for automated prompting and enhanced human-model interactions of SAM and SAM2 for the sake of promoting their widespread clinical adoption. Specifically, we propose Proxy Prompt …

Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

In this work, we study the logarithmic regret for reinforcement learning (RL) with linear function approximation and adversarial corruptions, in the formulation of linear Markov decision processes (MDPs). Specifically, we consider the case where there …

An Efficient Second-Order Approach to Factorize Sparse Matrices in Recommender Systems

2015 · IEEE Transactions on Industrial Informatics

Recommender systems are an important kind of learning systems, which can be achieved by latent-factor (LF)-based collaborative filtering (CF) with high efficiency and scalability. LF-based CF models rely on an optimization process with respect to …

A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method

2015 · IEEE Transactions on Neural Networks and Learning Systems

Nonnegative matrix factorization (NMF)-based models possess fine representativeness of a target matrix, which is critically important in collaborative filtering (CF)-based recommender systems. However, current NMF-based CF recommenders suffer from the problem of high computational and …

Collaborative Filtering Bandits

2016

Classical collaborative filtering, and content-based filtering methods try to learn a static recommendation model given training data. These approaches are far from ideal in highly dynamic recommendation domains such as news recommendation and computational advertisement, …