A Python Toolbox for Multimode Neural Data Representation Analysis - A Representational Analysis Toolbox for Neuroscience, including Representational Similarity Analysis (RSA), & Inter-Subject Correlation (ISC)
CKA (Centered Kernel Alignment) implemented in PyTorch
Tutorial on representational similarity analysis for MIND 2018
Analysis and investigating the confounding effect of accents in end-to-end Automatic Speech Recognition 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.
Representation Similarity Analysis (RSA) to measure the similarity of the feature maps extracted by two models.
A theoretical and empirical framework for measuring when two self-supervised learning views can effectively share a common linear encoder.
Predict how well a transfer-learning dataset will work before spending compute on fine-tuning.
To associate your repository with the representation-similarity topic, visit your repo's landing page and select "manage topics."