Search Results for author: Yedi Zhang

Found 10 papers, 5 papers with code

When Are Bias-Free ReLU Networks Like Linear Networks?

no code implementations18 Jun 2024 Yedi Zhang, Andrew Saxe, Peter E. Latham

This allows us to give closed-form time-course solutions to certain two-layer bias-free ReLU networks, which has not been done for nonlinear networks outside the lazy learning regime.

A Proactive and Dual Prevention Mechanism against Illegal Song Covers empowered by Singing Voice Conversion

no code implementations30 Jan 2024 Guangke Chen, Yedi Zhang, Fu Song, Ting Wang, Xiaoning Du, Yang Liu

To improve the imperceptibility of perturbations, we refine a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices.

Voice Conversion

Towards Efficient Verification of Quantized Neural Networks

1 code implementation20 Dec 2023 Pei Huang, Haoze Wu, Yuting Yang, Ieva Daukantas, Min Wu, Yedi Zhang, Clark Barrett

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory.


Understanding Unimodal Bias in Multimodal Deep Linear Networks

1 code implementation1 Dec 2023 Yedi Zhang, Peter E. Latham, Andrew Saxe

This is the first work to calculate the duration of the unimodal phase in learning as a function of the depth at which modalities are fused within the network, dataset statistics, and initialization.

QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems

no code implementations23 May 2023 Guangke Chen, Yedi Zhang, Zhe Zhao, Fu Song

Current adversarial attacks against speaker recognition systems (SRSs) require either white-box access or heavy black-box queries to the target SRS, thus still falling behind practical attacks against proprietary commercial APIs and voice-controlled devices.

Speaker Recognition

QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks

1 code implementation10 Dec 2022 Yedi Zhang, Zhe Zhao, Fu Song, Min Zhang, Taolue Chen, Jun Sun

Experimental results on QNNs with different quantization bits confirm the effectiveness and efficiency of our approach, e. g., two orders of magnitude faster and able to solve more verification tasks in the same time limit than the state-of-the-art methods.


QEBVerif: Quantization Error Bound Verification of Neural Networks

1 code implementation6 Dec 2022 Yedi Zhang, Fu Song, Jun Sun

In this work, we propose a quantization error bound verification method, named QEBVerif, where both weights and activation tensors are quantized.


BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks

no code implementations12 Mar 2021 Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Taolue Chen

Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications.


Making Agents' Abilities Explicit

no code implementations27 Nov 2018 Yedi Zhang, Fu Song, Taolue Chen

Alternating-time temporal logics (ATL/ATL*) represent a family of modal logics for reasoning about agents' strategic abilities in multiagent systems (MAS).

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