A promising approach to autonomous driving is machine learning. In machine learning systems, training datasets are created that capture the sensory input to a vehicle as well as the desired response. One disadvantage of using a learned navigation system is that the learning process itself may require both a huge number of training examples and a large amount of computing. To avoid the need to collect a large training set of driving examples, we describe a system that takes advantage of the immense number of training examples provided by ImageNet, but at the same time is able to adapt quickly using a small training set for the driving environment.