Feng Zhou

Application of improved multiple convolution neural network in emotion polarity classification model

2017

In view of the emotional polarity classification problem, the deep learning has the disadvantages of incomplete information extraction and low precision, a model combining bi-directional gated recurrent unit with multiple convolution neural network is proposed. …

Accelerated Linearized Laplace Approximation for Bayesian Deep Learning

2022 · arXiv (Cornell University)

Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks. The generalized Gauss-Newton (GGN) approximation is typically introduced to improve their tractability. However, LA and …

Accelerating Convergence in Bayesian Few-Shot Classification

2024 · arXiv (Cornell University)

Bayesian few-shot classification has been a focal point in the field of few-shot learning. This paper seamlessly integrates mirror descent-based variational inference into Gaussian process-based few-shot classification, addressing the challenge of non-conjugate inference. By leveraging …