Matrices of the derivative of vectors with respect to vectors (Jacobians) take a specific form: Here, note that each column is the partial of f with respect to one component , whereas each row is the partial of with respect to the . That is, the rowsÂ ‘cover’ the range of f. You can then easily remember that C: the columns … Read More

## RNNs as State-space Systems

It’s fantastic how you can often use concepts from one field to investigate ideas in another area and improve your understanding of both areas. That’s one of the things I enjoy most. We’ve just started studying state-space models in 3F2 Systems and Control (a third-year Engineering course at Cambridge). It’s reminded me strongly of recurrent neural networks (RNNs). Look at … Read More