all AI news
A Modern Self-Referential Weight Matrix That Learns to Modify Itself. (arXiv:2202.05780v2 [cs.LG] UPDATED)
June 20, 2022, 1:11 a.m. | Kazuki Irie, Imanol Schlag, Róbert Csordás, Jürgen Schmidhuber
cs.LG updates on arXiv.org arxiv.org
The weight matrix (WM) of a neural network (NN) is its program. The programs
of many traditional NNs are learned through gradient descent in some error
function, then remain fixed. The WM of a self-referential NN, however, can keep
rapidly modifying all of itself during runtime. In principle, such NNs can
meta-learn to learn, and meta-meta-learn to meta-learn to learn, and so on, in
the sense of recursive self-improvement. While NN architectures potentially
capable of implementing such behaviour have been …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US