scientific article; zbMATH DE number 7370557

MaRDI QIDQ4998929zbMATH OpenFDO

Authors Anton Bakhtin, Yuntian Deng, Sam Gross, Myle Ott, Marc'Aurelio Ranzato, Arthur Szlam

Publication date 9 July 2021

Full work available at URL https://arxiv.org/abs/2004.10188, https://jmlr.csail.mit.edu/papers/v22/20-326.html

zbMATH Keywords

energy-based modelsgeneralizationimportance samplingnegative samplingreal/fake discriminationtext generation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• 10.1162/jmlr.2003.4.7-8.1235
• A decision-theoretic generalization of on-line learning and an application to boosting
• A Generalization of Sampling Without Replacement From a Finite Universe
• scientific article; zbMATH DE number 6276120 (Why is no real title available?)
• Neural networks and physical systems with emergent collective computational abilities
• Training Products of Experts by Minimizing Contrastive Divergence

Describes a project that uses

Uses Software

• SGDR
• CTRL
• PyTorch
• Tensor2Tensor
• GPT-3
• Adam
• SeqGAN
• BERT
• fairseq

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998929)