Layer-Wise Partitioning and Merging for Efficient and Scalable Deep Learning
نویسندگان
چکیده
منابع مشابه
Layer-wise learning of deep generative models
When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. We interpret autoencoders in this setting as generative models, by showing tha...
متن کاملDeep Learning Layer-wise Learning of Feature Hierarchies
Hierarchical neural networks for object recognition have a long history. In recent years, novel methods for incrementally learning a hierarchy of features from unlabeled inputs were proposed as good starting point for supervised training. These deep learning methods— together with the advances of parallel computers—made it possible to successfully attack problems that were not practical before,...
متن کاملCollaborative Layer-Wise Discriminative Learning in Deep Neural Networks
Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples of different complexities. For example, if a training sample has already been correctly classified at a specific layer with high confidence, we argue that it ...
متن کاملCost-Sensitive Deep Learning with Layer-Wise Cost Estimation
While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural ne...
متن کاملEfficient and scalable parallel graph partitioning
The realization of efficient parallel graph partitioners requires the parallelization of the multi-level framework which is commonly used to improve the quality and speed of sequential partitioners. The two most critical issues in this framework are the coarsening phase, and the local refinement step performed in the uncoarsening phase. These two phases are difficult to parallelize, because the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Social Science Research Network
سال: 2022
ISSN: ['1556-5068']
DOI: https://doi.org/10.2139/ssrn.4279818