hAIgopala › AI terms › Rapid Fire (3 terms per short) › Day 12

RNN / LSTM

Neural Networks & Deep LearningChapter 3: Inside the BrainTerm 53 of 253

Networks for sequences that keep memory of previous inputs. Largely replaced by Transformers.

At Sunrise School

Gopal asks

What came before Transformers for reading sentences?

Bit answers

RNNs and LSTMs read word by word, carrying a memory. They struggled with long messages, so Transformers replaced them.

In the real world

Older speech recognition and translation.

Watch the short

Short coming soonSeason 5 · Day 12Follow @haigopala

Taught together with

CNN (Convolutional Neural Network) · Autoencoder

Practise it

Try this term and all 253 others in the free Model Training Arena.

Open the Arena →

Follow Bit daily: YouTube English · తెలుగు · हिंदी  |  Instagram English · తెలుగు · हिंदी