Which specific type of RNN was designed to mitigate the vanishing gradient problem using a 'forget gate'?

Show answer

LSTM

Long Short-Term Memory (LSTM) networks use a cell state and three gates (input, forget, and output) to regulate the flow of information. This architecture allows the network to maintain information over long sequences more effectively than vanilla RNNs.

Also asked as:

What specific type of Recurrent Neural Network uses a cell state and a gated architecture to maintain information over long sequences more effectively than vanilla RNNs?

Would you remember this in 6 months?

Trivia Forge uses spaced repetition so facts stick. Free, no signup needed.

Turn on Machine Learning practice →

More Machine Learning trivia

Which technique improves neural network training by normalizing layer inputs to have a mean of zero and a variance of one for each mini-batch?
Which theorem states that there is no single machine learning algorithm that performs better than all others across every possible problem?
Which three researchers are often credited with the 1986 seminal paper on the backpropagation algorithm?
Who developed the neocognitron, a hierarchical multilayered neural network that inspired modern Convolutional Neural Networks?
Who is credited with proving the Universal Approximation Theorem for sigmoid activation functions in 1989?
Who is often credited with developing the first artificial neural network called the 'Perceptron' in 1958?

See all 98 →