Continuous-Time Neural Networks Can Stably Memorize and Reproduce Random Spike Trains
Continuous-time recurrent neural networks can robustly memorize and autonomously reproduce arbitrary random spike train patterns with stable accurate relative timing of all spikes, within some range of parameters.
Stability Analysis and Control Design for Recurrent Neural Network-Based Systems
This paper proposes novel global and regional stability analysis conditions based on linear matrix inequalities for a general class of recurrent neural networks. These conditions can be used for state-feedback control design.
명시적 NeRF 모델 압축을 위한 품질 평가 데이터베이스: Explicit-NeRF-QA
명시적 NeRF 모델의 압축 연구를 위해 다양한 기하학, 텍스처 및 재질 복잡성을 가진 3D 객체를 사용하여 Explicit-NeRF-QA 데이터셋을 구축하였다. 이를 통해 NeRF 모델의 고유한 왜곡 유형을 체계적으로 정의하고, 기존 객관적 화질 평가 지표의 성능을 평가하였다.
Efficient Autoencoder Architecture for Modeling the Lateral Geniculate Nucleus by Integrating Feedforward and Feedback Streams in the Human Visual System
The proposed pruned autoencoder (pAE) model effectively simulates the lateral geniculate nucleus (LGN) function by integrating feedforward and feedback streams from/to the primary visual cortex (V1), outperforming other models and human benchmarks in visual object categorization tasks.
A Novel Method for Simultaneous Facial Expression Transfer and Audio-Driven Lip Synchronization in Talking Face Generation
A novel NeRF-based method that simultaneously combines lip-syncing to a target audio with facial expression transfer to generate high-fidelity talking faces.
A Unified Framework for Neural Computation and Learning from Continuous Data Streams
This paper proposes Hamiltonian Learning, a novel unified framework for learning with neural networks from a possibly infinite stream of data, in an online manner, without having access to future information.
An Artificial Neural Network for Image Classification Inspired by the Aversive Olfactory Learning Circuits of Caenorhabditis Elegans
This study introduces an artificial neural network (ANN) for image classification that is inspired by the aversive olfactory learning circuits of the nematode Caenorhabditis elegans, demonstrating superior performance compared to control networks.
Synchronized Talking Head Synthesis: Addressing the Challenges of Consistent Identity, Lip Movements, Facial Expressions, and Head Poses
To achieve highly synchronized and realistic speech-driven talking head synthesis, SyncTalk effectively maintains subject identity, enhances synchronization of lip movements, facial expressions, and head poses, and improves visual quality through a novel NeRF-based framework.
時間依存性を持つ多機能性のニューラルユニット: スプリングとストップウォッチ
単一の動的ニューラルユニットが、同一の動的軌道の中で、時間によって異なる非線形計算を実行できる。
Efficient Neural Architecture Search Using a Forward-and-Reverse Graph Predictor
A novel graph-based performance predictor that leverages both forward and reverse representations of neural architectures to enhance prediction accuracy, especially in data-limited settings.
© 2024 by Linnk AI