JohnVorwald
JohnVorwald
Consider reformulating the formuation, and coding, including threshold functions, using matrix expressions, instead of all the low level loops. Then the output error function can be more general, depending on...
In backpropagation, you mention recurrent input, for feedback. I'm having trouble locating that coding.
System: Ubuntu 18.04 Command: make samples Abort due to errors in line 340 of synthetic.cc Output of "make samples" /MYNT-EYE-S-SDK-master/src/mynteye/api/synthetic.cc:340:26: error: no matching function for call to ‘make_shared(std::shared_ptr, std::shared_ptr, std::shared_ptr,...
Below is a simple rnn that runs on some input to generate the output. The input and output are split into train / test. The model is fitted with the...