Search Results for author:
Found 4 papers, 1 papers with code
Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment
Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities.
Sparse Binary Transformers for Multivariate Time Series Modeling
Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments.
Randomly Initialized Subnetworks with Iterative Weight Recycling
In addition to Iterative Weight Recycling, we complement the Multi-Prize Lottery Ticket Hypothesis with a reciprocal finding: high-accuracy, randomly initialized subnetwork's produce diverse masks, despite being generated with the same hyperparameter's and pruning strategy.
Utilizing Network Properties to Detect Erroneous Inputs
Neural networks are vulnerable to a wide range of erroneous inputs such as adversarial, corrupted, out-of-distribution, and misclassified examples.
