The Fastest, Memory-efficient Python Library for layer-wise similarity computation between neural network models
Predict how well a transfer-learning dataset will work before fine-tuning on it. TLDChoiceNet cuts prediction MSE 5x, and an unsupervised class-correlation metric explains fine-tune accuracy with R2=0.97. Stanford CS 330.
A diagnostic control paradigm for activation measurements in transformer language models. Cross-replay separates text-bound from architecture-bound components by replaying generated sequences through intact and perturbed model variants.
Predict how well a transfer-learning dataset will work before spending compute on fine-tuning.
A Centered Kernel Alignment implementation with distributed GPU support.
Add a description, image, and links to the centered-kernel-alignment topic page so that developers can more easily learn about it.
To associate your repository with the centered-kernel-alignment topic, visit your repo's landing page and select "manage topics."