🏢 Graduate School of AI, KAIST
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
·4111 words·20 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 Graduate School of AI, KAIST
DASH combats neural network training’s plasticity loss during warm-starting by selectively forgetting memorized noise while preserving features, improving accuracy and efficiency.