Gradient-based learning drives robust representations in recurrent neural networks by balancing compression and expansion
Matthew Farrell, Stefano Recanatesi, Timothy C. Moore, Guillaume Lajoie, Eric Shea‐Brown
Topics & Concepts
Recurrent neural networkCurse of dimensionalityComputer scienceGradient descentChaoticArtificial intelligenceArtificial neural networkGeneralizationMachine learningMathematicsMathematical analysisNeural dynamics and brain functionAdvanced Memory and Neural ComputingNeural Networks and Applications