User:Steven189/sandbox/Catastrophic Interference

Catastrophic Interference new article content

Latent Learning

Latent Learning is a transfer learning technique used by Gutstein & Stump (2015) both to mitigate catastrophic interference and to help learn new information by using existing knowledge. Rather than manipulating the representations used by hidden nodes, this approach optimizes the representations trained into the output nodes. It chooses output encodings for new classes that are least likely to catastrophically interfere with existing responses. Given a net that has learned to discriminate among one set of classes using Error Correcting Output Codes (ECOC), instead of 1 hot codes , optimal encodings for new classes are chosen by observing the net's average responses to them. Since these average responses arose while learning the original set of classes without any exposure to the new classes, they are referred to as 'Latently Learned Encodings'. This terminology borrows from the concept of Latent Learning, as introduced by Tolman in 1930. In effect, this technique uses transfer learning to avoid catastrophic interference.