Deep Learning
When Does Confidence-Based Cascade Deferral Suffice? Wittawat Jitkrittum Neha Gupta Aditya Krishna Menon Harikrishna Narasimhan Ankit Singh Rawat Sanjiv Kumar Google Research, New York
One simple deferral rule employs the confidence of the current classifier, e.g., based on the maximum predicted softmax probability.
Empowering Convolutional Neural Networks with MetaSin Activation
This work was done while the author was an intern at Disney Research | Studios 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
Semantic HELM: A Human-Readable Memory for Reinforcement Learning Fabian Paischer 1, Thomas Adler
In this regard, we propose a novel memory mechanism that represents past events in human language.
DataComp-LM: Insearchofthenextgenerationof trainingsetsforlanguagemodels
Asabaseline for DCLM, we conduct extensive experiments and find that model-based filtering is key to assembling a high-quality training set.
