8/10) We find that α correlates more strongly to downstream task performance than the #BarlowTwins loss itself! 🤯
Thus, we propose a model selection #algorithm based on this result to reduce the number of #readout evals required to identify the best #hyperparamaters. 🤓
#neuroscience #deeplearning #ml #ai #hyperparamaters #readout #algorithm #barlowtwins