A review on dropout regularization approaches for deep neural networks within the scholarly domain
Dropout is one of the most popular regularization methods in the scholarly domain for
preventing a neural network model from overfitting in the training phase. Developing an …
preventing a neural network model from overfitting in the training phase. Developing an …
Do not have enough data? Deep learning to the rescue!
A Anaby-Tavor, B Carmeli, E Goldbraich… - Proceedings of the AAAI …, 2020 - aaai.org
Based on recent advances in natural language modeling and those in text generation
capabilities, we propose a novel data augmentation method for text classification tasks. We …
capabilities, we propose a novel data augmentation method for text classification tasks. We …
Survey of dropout methods for deep neural networks
Dropout methods are a family of stochastic techniques used in neural network training or
inference that have generated significant research interest and are widely used in practice …
inference that have generated significant research interest and are widely used in practice …
Gmail smart compose: Real-time assisted writing
In this paper, we present Smart Compose, a novel system for generating interactive, real-
time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In …
time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In …
Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs
We consider a simple and overarching representation for permutation-invariant functions of
sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses …
sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses …
Co-regularized alignment for unsupervised domain adaptation
Deep neural networks, trained with large amount of labeled data, can fail to generalize well
when tested with examples from a target domain whose distribution differs from the training …
when tested with examples from a target domain whose distribution differs from the training …
Evolutionary stochastic gradient descent for optimization of deep neural networks
We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD)
framework for optimizing deep neural networks. ESGD combines SGD and gradient-free …
framework for optimizing deep neural networks. ESGD combines SGD and gradient-free …
IAUnet: Global context-aware feature learning for person reidentification
Person reidentification (reID) by convolutional neural network (CNN)-based networks has
achieved favorable performance in recent years. However, most of existing CNN-based …
achieved favorable performance in recent years. However, most of existing CNN-based …
SCL-CVD: Supervised contrastive learning for code vulnerability detection via GraphCodeBERT
Detecting vulnerabilities in source code is crucial for protecting software systems from
cyberattacks. Pre-trained language models such as CodeBERT and GraphCodeBERT have …
cyberattacks. Pre-trained language models such as CodeBERT and GraphCodeBERT have …
Simplified multilayer graph convolutional networks with dropout
F Yang, H Zhang, S Tao - Applied Intelligence, 2022 - Springer
Graph convolutional networks (GCNs) and their variants are excellent deep learning
methods for graph-structured data. Moreover, multilayer GCNs can perform feature …
methods for graph-structured data. Moreover, multilayer GCNs can perform feature …