Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Zhang, Yedi"'
We investigate the expressivity and learning dynamics of bias-free ReLU networks. We firstly show that two-layer bias-free ReLU networks have limited expressivity: the only odd function two-layer bias-free ReLU networks can express is a linear one. W
Externí odkaz:
http://arxiv.org/abs/2406.12615
Singing voice conversion (SVC) automates song covers by converting one singer's singing voice into another target singer's singing voice with the original lyrics and melody. However, it raises serious concerns about copyright and civil right infringe
Externí odkaz:
http://arxiv.org/abs/2401.17133
Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying properties of
Externí odkaz:
http://arxiv.org/abs/2312.12679
Using multiple input streams simultaneously to train multimodal neural networks is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where a network overly relies on one modality and ignores others during joint t
Externí odkaz:
http://arxiv.org/abs/2312.00935
Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has focused on s
Externí odkaz:
http://arxiv.org/abs/2309.07983
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
Externí odkaz:
http://arxiv.org/abs/2305.14097
Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are limited on reso
Externí odkaz:
http://arxiv.org/abs/2212.11138
To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge devices, quantization is widely regarded as one promising technique. It reduces the resource requirements for computational power and storage space by quantizing
Externí odkaz:
http://arxiv.org/abs/2212.02781
Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks (BNNs), the 1-
Externí odkaz:
http://arxiv.org/abs/2103.07224
Alternating-time temporal logics (ATL/ATL*) represent a family of modal logics for reasoning about agents' strategic abilities in multiagent systems (MAS). The interpretations of ATL/ATL* over the semantic model Concurrent Game Structures (CGS) usual
Externí odkaz:
http://arxiv.org/abs/1811.10901