mu578

@msrdinesh, @codeplea hello any follow up on that matter? Have a good day.

@lucasart computing the derivative is not the problem, the problem is to have a redesign of the code that reflects the current activation function, so something needs to be known...

@lucasart ; the implementation is interesting; meanwhile, I would go deeper, adding a layer of indirection on any internal arithmetic operations then moving `nn_float_t` to `nn_numeric_t` or so ; thus,...

On top use that instead of forcing the _POSIX_C_SOURCE define : ```C # if defined(__APPLE__) # include # else # ifndef _POSIX_C_SOURCE # define _POSIX_C_SOURCE 200809L # endif # endif...

@hello, (not directly related to, but somehow it is) for people writing C/C++ programs, we (I) re-wrote from scratch a full reference implementation (minus complex; work in progress) of fortran-blas...

@derpda yes I understand; I am shaping the future (LOL); it's only few weeks of spare time work; however, it's building up; I have been delayed by other matters in...

certainly is the word; that's the reason I am doing it; even if an algorithm has been thought and shape taking advantages of column-major access. There is no comparison in...

Hello, thank you, ye, I am looking for a pre-computed set of diags of the bidiags matrices and their expected outputs; for instance, in q2 there is a comment about...

If you have fortran test routines; I am interested in; however, nothing available here; + it took me two days to enter *lasq* "code", what a nightmare :). Maybe having...

hello, please feel free to scavenge things there, might help you to get rid of bottlenecks. I suspect a too low tol settings https://github.com/moe123/macadam/tree/master/macadam/details/numa