How should we compare neural network representations? – The Berkeley Artificial Intelligence Research Blog

bair.berkeley.edu · 1,091 words · saved by 1 readers

To understand neural networks, researchers often use similarity metrics to measure how similar or different two neural networks are to each other. For instance, they are used to compare vision transformers to convnets [1], to understand transfer learning [2], and to explain the success of standard training practices for deep models [3]. Below is an example visualization using similarity metrics; specifically we use the popular CKA similarity metric (introduced in [4]) to compare two transformer models across different layers: Figure 1. CKA (Centered Kernel Alignment) similarity between two networks trained identically except for random initialization. Lower values (darker colors) are more similar. CKA suggests that the two networks have similar representations. Unfortunately, there isn’t much agreement on which particular similarity metric to use. Here’s the exact same figure, but produced using the Canonical Correlation Analysis (CCA) metric instead of CKA: Figure 2. CCA (Canonical

Cross-posted from Bounded Regret . To understand neural networks, researchers often use similarity metrics to measure how similar or different two neural networks are to each other. For instance, they are used to compare vision transformers to convnets [1], to understand transfer learning [2], and to explain the success of standard training practices for deep models [3]. Below is an example visualization using similarity metrics; specifically we use the popular CKA similarity metric (introduced in [4]) to compare two transformer models across different layers: Figure 1. CKA (Centered Kernel Al

How should we compare neural network representations? – The Berkeley Artificial Intelligence Research Blog

related reading