Our rule may be understood as ageneralization of contrastive Hebbian learning to meta-learning and notably, it neither requires computing second derivativesnorgoing backwardsintime,twocharacteristic features of previous gradient-based methods that are hard to conceive in physicalneuralcircuits.

Vision-and-Language Navigation requires the agent to follow language instructions to navigate through 3D environments.

In ICL, a conditional generative model (CGM) is prompted with a dataset and a prediction question and asked to generate a response.