Update blog/_posts/2019-01-18-fluxdiffeq.md

Co-Authored-By: ChrisRackauckas <[email protected]>

blog/_posts/2019-01-18-fluxdiffeq.md

@@ -606,7 +606,7 @@ Flux.train!(loss_n_ode, ps, data, opt, cb = cb)
 
 ![Neural ODE Train](https://user-images.githubusercontent.com/1814174/51585825-dc3f8480-1ea8-11e9-8498-18cf55fba3e6.gif)
 
-Notice that what's not being learned is the solution to the ODE.
+Notice that we are not learning a solution to the ODE.
 Instead, what we are learning is the tiny ODE system from which the ODE
 solution is generated. I.e., the neural network inside the neural_ode
 layer learns this function: