2 Matching Annotations
  1. Feb 2019
    1. What I will call the model (M) which is our previous neural net. It can now be seen as a low-level network. It is sometimes called an optimizee or a learner. The weights of the model are the ■ on the drawings.The optimizer (O) or meta-learner is a higher-level model which is updating the weights of the lower-level network (the model). The weights of the optimizer are the ★ on the drawings



    2. From zero to research — An introduction to Meta-learning


      what happens when we train a simple neural net to classify images of dogs and cats.