Posts

Showing posts from February 10, 2019

Helsingia (Finnia)

Image
Helsingia Finnice: Helsinki Suecice: Helsingfors Insigne Situs Situs Helsingiae in Finnia Nomina Latina alia Helsingforsia, Helsinkium Res politicae Regio Nylandia Magister Iohannes (Jussi) Pajunen Res geographicae Area  - tota  - terrestris  - aquosa 187.1 km² 186.4 km² 0.7 km² Numerus incolarum 2015  - Spissitudo  - Tractus metropolitanus 624 427 3 010 incolae/km² 1 288 781 Situs interretialis: http://www.hel.fi Helsingia, [1] vel Helsinkium, [2] Helsingforsa [3] , vel Helsingforsia [4] vel Forsia Helsingiorum [5] vel Helsingia Nova [6] (Finnice: Helsinki, IPA [hɛlsiŋki]; Suecice: Helsingfors ), est urbs principalis et caput Finniae. Urbi sunt circiter 624 400 incolarum. Regio capitis vicinae urbes Vantaniam et Esboam et Grankullam continet, quae una regionem capitalem faciunt. Circiter 992 836 hominum regionem incolunt. Area metropolitana Helsingiensis alias urbes continet et est circiter 1 293 093 incolar...

Gradient of NN output with respect to inputs

Image
0 $begingroup$ I've trained a neural net on a problem where multiple inputs can be mapped to the same output. I'd like to use this NN to go from an output to an input i.e. given an output vector $y$ , I want to find an input $x$ such that the NN returns some $z$ close to the given output $y$ when fed input $x$ . I was thinking of using gradient descent to do this - do any of the common deep learning APIs let you take gradients of NNs with respect to their inputs? I've looked around and haven't found anything, but figured I'd check here before moving forward. machine-learning neural-network deep-learning tensorflow pytorch share | improve this question ...