rakeshvar

Element-wise logisticloss on Vectors || Column-wise logsumexp on Matrices

2

I want to apply the function `log(1+exp(.))` on a vector element-wise; then take an inner product with another positive vector (making the whole thing convex). I see that the function...

In Python one can do this: ```python geopoint = {'latitude':41.123,'longitude':71.091} '{latitude} {longitude}'.format(**geopoint) ``` One can even do this apparently. Which does not look very hygienic. ```python '{0[latitude]} {0[longitude]}'.format(geopoint) 'The title...

https://github.com/MikeInnes/diff-zoo/blob/9f48c85a8a846b3603ef4d86afd023144915abf9/src/utils.jl#L130 It should be `divm` (not `mulm`).

Thank you for this extremely wonderful tutorial. I learnt a lot. Also please mention that they need to read `backandforth.ipynb` after the `intro.ipynb`. It makes most sense that way. And...