News

IEEE19d
Dynamic Summarization of Videos Based on Descriptors in Space-Time Video Volumes and Sparse Autoencoder
The sparse autoencoder (SAE), an instance of deep learning strategy, is used for the extraction of high-level features from LPQ-TOP descriptors to represent the shots carrying key-contents of videos ...
IEEE23d
Multi-Fault Diagnosis Using Stacked Sparse Autoencoder Model
The present paper studies the performance of stacked sparse autoencoder (SSAE) on the multi-fault diagnosis of bearing and shaft components based on image classification. The vibration signal is ...
Frontiers29d
Integrating multi-source monitoring data and deep convolutional autoencoder technology for slope failure pattern recognition
The architecture of the model is shown in Figure 5. Figure 5. Model architecture diagram of the deep convolutional autoencoder. The input to the model is a 9 × 24 matrix, where 9 represents the 9 ...
GitHub29d
“Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval.”
To train the SAE, you need embeddings generated by a DPR model. We use dense embeddings from SimLM for all 8.8M MSMARCO passages and train queries. After training the SAE, you can reconstruct the ...