Explain self.wi = rand_arr(-0.1, 0.1, mem_cell_ct, concat_len)

nicodjimenez / lstm

Minimal, clean example of lstm neural network training in python, for learning purposes.

1.72k stars 654 forks source link

Explain self.wi = rand_arr(-0.1, 0.1, mem_cell_ct, concat_len) #27

Open shaifugpt opened 6 years ago

shaifugpt commented 6 years ago

what does self.wi = rand_arr(-0.1, 0.1, mem_cell_ct, concatlen) signify? Is wi having input gate weights for both input x{t} as well as the h_{t-1}. What does mem_cell_ct contain and what is concat_len