Search Results for author: Siyu Lou

Found 6 papers, 3 papers with code

Defining and Extracting generalizable interaction primitives from DNNs

no code implementations29 Jan 2024 Lu Chen, Siyu Lou, Benhao Huang, Quanshi Zhang

Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI.

Physics-constrained robust learning of open-form PDEs from limited and noisy data

no code implementations14 Sep 2023 Mengge Du, Longfeng Nie, Siyu Lou, Yuntian Chenc, Dongxiao Zhang

The embedding phase integrates the initially identified PDE from the discovering process as a physical constraint into the predictive model for robust training.

Reinforcement Learning (RL)

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

1 code implementation4 Apr 2023 Lu Chen, Siyu Lou, Keyan Zhang, Jin Huang, Quanshi Zhang

The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network.

Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts

1 code implementation25 Feb 2023 Qihan Ren, Huiqi Deng, Yunuo Chen, Siyu Lou, Quanshi Zhang

In this paper, we focus on mean-field variational Bayesian Neural Networks (BNNs) and explore the representation capacity of such BNNs by investigating which types of concepts are less likely to be encoded by the BNN.

Audio-text Retrieval in Context

no code implementations25 Mar 2022 Siyu Lou, Xuenan Xu, Mengyue Wu, Kai Yu

Using pre-trained audio features and a descriptor-based aggregation method, we build our contextual audio-text retrieval system.

AudioCaps Retrieval +1

Cannot find the paper you are looking for? You can Submit a new open access paper.