Continual learning by using task conditional neural networks
Honglin Li, Payam Barnaghi, Shirin Enshaeifar, Frieder Ganz · arXiv (Cornell University) · 2019
Task Conditional Neural Networks (TCNN) leverage the probabilistic neural networks to estimate the probability density of the training samples. Then produce the task likelihood during the test state to fire the task-specific neurons corresponding to the test samples. TCNN can detect and learn the new tasks fully-automatically without informing the changes to the model