Author: Celaya, Adrian; Actor, Jonas A.; Muthusivarajan, Rajarajeswari; Gates, Evan; Chung, Caroline; Schellingerhout, Dawid; Riviere, Beatrice; Fuentes, David
Title: PocketNet: A Smaller Neural Network for Medical Image Analysis Cord-id: e421wnz1 Document date: 2021_4_21
ID: e421wnz1
Snippet: Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by throttling the growth of the number of channels in convolutional neural networks. We demonstrate that, for a range of segmentation and classification tasks, PocketNet architectures produce results comparable to that of conventional neural networks while reducing
Document: Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by throttling the growth of the number of channels in convolutional neural networks. We demonstrate that, for a range of segmentation and classification tasks, PocketNet architectures produce results comparable to that of conventional neural networks while reducing the number of parameters by multiple orders of magnitude, using up to 90% less GPU memory, and speeding up training times by up to 40%, thereby allowing such models to be trained and deployed in resource-constrained settings.
Search related documents:
Co phrase search for related documents- accuracy score and loss function: 1, 2
- accuracy score and loss function entropy: 1
Co phrase search for related documents, hyperlinks ordered by date