“…Modern deep learning systems are generally unable to adapt to a sudden reordering of sensory inputs, unless the model is retrained, or if the user manually corrects the ordering of the inputs for the model. However, techniques from continual meta-learning, such as adaptive weights [2,35,64], Hebbian-learning [51,52,56], and model-based [1,19,36,37] approaches can help the model adapt to such changes, and remain a promising active area of research.…”