Enhancing Deep Learning
Sara discusses the importance of inductive priors in improving sample efficiency and the need to treat examples differently in deep neural networks to enhance generalization. She highlights the impact of sparsity-based training as a potential solution to mitigate over-parameterization and increase efficiency in deep learning models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Sara Hooker - The Hardware Lottery, Sparsity and Fairness
Related Questions