most citedReduce, Reuse, Recycle: Improving Training Efficiency with Distillation

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

cs.LG20221 cited

Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation

Cody Blakeney, Jessica Zosa Forde, Jonathan Frankle +2

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning prac…

cs.CY2020

Towards falsifiable interpretability research

Matthew L. Leavitt, Ari Morcos

Methods for understanding the decisions of and mechanisms underlying deep neural networks (DNNs) typically rely on building intuition by emphasizing sensory or semantic features of…

cs.LG2020

Linking average- and worst-case perturbation robustness via class selectivity and dimensionality

Matthew L. Leavitt, Ari Morcos

Representational sparsity is known to affect robustness to input perturbations in deep neural networks (DNNs), but less is known about how the semantic content of representations a…

cs.LG2020

On the relationship between class selectivity, dimensionality, and robustness

Matthew L. Leavitt, Ari S. Morcos

While the relative trade-offs between sparse and distributed representations in deep neural networks (DNNs) are well-studied, less is known about how these trade-offs apply to repr…

cs.LG2020

Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs

Matthew L. Leavitt, Ari Morcos

The properties of individual neurons are often analyzed in order to understand the biological and artificial neural networks in which they're embedded. Class selectivity-typically…