RNNbow: Visualizing Learning Via Backpropagation Gradients in RNNs
| Autor: | Dylan Cashman, Genevieve Patterson, Nathan Watts, Abigail Mosca, Remco Chang, Shannon Robinson |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
business.industry
Computer science Process (computing) 020207 software engineering 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Computer Graphics and Computer-Aided Design Backpropagation Recurrent neural network 0202 electrical engineering electronic engineering information engineering Artificial intelligence business computer Software 0105 earth and related environmental sciences |
| Zdroj: | IEEE Computer Graphics and Applications. 38:39-50 |
| ISSN: | 1558-1756 0272-1716 |
| DOI: | 10.1109/mcg.2018.2878902 |
| Popis: | We present RNNbow, an interactive tool for visualizing the gradient flow during backpropagation in training of recurrent neural networks. By visualizing the gradient, as opposed to activations, RNNbow offers insight into how the network is learning. We show how it illustrates the vanishing gradient and the training process. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|