Researchers from Vanderbilt University and UC Davis Introduce PRANC: A Deep Learning Framework that is Memory-Efficient during both the Learning and Reconstruction Phases

Researchers from Vanderbilt University and the University of California, Davis, introduced PRANC, a framework demonstrating the reparameterization of a deep model as a linear combination of randomly initialized and frozen deep models in the weight space. During training, local minima within the subspace spanned by these basis networks are sought, enabling significant compaction of the […]

The post Researchers from Vanderbilt University and UC Davis Introduce PRANC: A Deep Learning Framework that is Memory-Efficient during both the Learning and Reconstruction …

ai shorts applications artificial intelligence california combination davis deep learning deep learning framework editors pick framework linear machine learning memory researchers space staff tech news technology uc davis university vanderbilt university