Question for AttentionLSTM

[verystrongjoe]

trafficstars

AttentionLSTM code is implemented by the author extending Recurrent layer module in Keras?

below, what i,f,c,o mean? What do they stand for?

        self.kernel_i = self.kernel[:, :self.units]
        self.kernel_f = self.kernel[:, self.units: self.units * 2]
        self.kernel_c = self.kernel[:, self.units * 2: self.units * 3]
        self.kernel_o = self.kernel[:, self.units * 3:]

[titu1994]

They are the 4 gates of the lstm cell - input, forget, context, output gates. I would suggest not using the attention lstm, for multivariate input it exhausts a lot of memory.