Content pfp
Content
@
0 reply
0 recast
0 reaction

Angel pfp
Angel
@angelcrypto
### Automatic differentiation in C++ ### Day 3: Today I focused on reading more about forward mode and refreshing some theory about chain rule and some gradients refresher (been a while since I've done those calculations by hand). I think I'll start with implementing forward mode first at this time.
1 reply
0 recast
0 reaction

Angel pfp
Angel
@angelcrypto
Also, I figuered I'll write my own little Tensor class as well, something similar to the pytorch one (but with less functionalities of course). I'll go on afterwards to add both modes of AD, starting with forward mode. Tomorrow, I'll start implementing that and start sharing real progress (and code!).
1 reply
0 recast
0 reaction

tobey pfp
tobey
@fklc
I've followed your suggestions and studied from the links you provided! Great stuff! 5000 $degen
2 replies
0 recast
0 reaction

tobey pfp
tobey
@fklc
Yeah and I can't wait to check the code as well!!
0 reply
0 recast
0 reaction