21 citations · 54 across the 18 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 1 cited
Machine learning in and out of equilibrium
Shishir Adhikari, Alkan Kabakçıoğlu, Alexander Strang +2
The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space --…
cs.LG2022★ 6 cited
Self-Supervised Learning with an Information Maximization Criterion
Serdar Ozsoy, Shadi Hamdan, Sercan Ö. Arik +2
Self-supervised learning allows AI systems to learn effective representations from large amounts of data using tasks that do not require costly labeling. Mode collapse, i.e., the m…