Tweeted By @evolvingstuff
A single-layer RNN can approximate stacked and bidirectional RNNs, and topologies in between
— Thomas Lahore (@evolvingstuff) September 4, 2019
"single-layer RNN can perfectly mimic an arbitrarily deep stacked RNN under specific constraints on its weight matrix and a delay between input and output"https://t.co/nmeasSiw0S pic.twitter.com/qbR1ms0fos