|
gptkbp:instance_of
|
gptkb:microprocessor
|
|
gptkbp:bfsLayer
|
3
|
|
gptkbp:bfsParent
|
gptkb:microprocessor
gptkb:Jürgen_Schmidhuber
|
|
gptkbp:allows
|
computationally intensive
difficult to interpret
requires large datasets
|
|
gptkbp:applies_to
|
speech recognition
video analysis
image captioning
|
|
gptkbp:characteristics
|
gptkb:gate
cell state
memory cell
|
|
gptkbp:developed_by
|
gptkb:Jürgen_Schmidhuber
gptkb:Sepp_Hochreiter
|
|
gptkbp:has_feature
|
forget gate
input gate
output gate
|
|
gptkbp:has_programs
|
gptkb:engine
chatbots
recommendation systems
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Long Short-Term Memory (LSTM)
|
|
gptkbp:improves
|
vanishing gradient problem
|
|
gptkbp:introduced
|
gptkb:1997
|
|
gptkbp:is_compared_to
|
gptkb:Gated_Recurrent_Unit_(GRU)
|
|
gptkbp:is_evaluated_by
|
accuracy
loss function
training time
|
|
gptkbp:is_influenced_by
|
gptkb:television_channel
input sequence length
training parameters
|
|
gptkbp:is_optimized_for
|
long-range dependencies
|
|
gptkbp:is_part_of
|
gptkb:microprocessor
|
|
gptkbp:is_popular_in
|
gptkb:robot
financial forecasting
time series analysis
healthcare analytics
|
|
gptkbp:is_related_to
|
attention mechanisms
transformer models
sequence-to-sequence models
|
|
gptkbp:is_used_for
|
language translation
natural language processing
sentiment analysis
time series forecasting
text generation
sequence prediction
|
|
gptkbp:is_used_in
|
gptkb:Graphics_Processing_Unit
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:related_to
|
gptkb:Artificial_Intelligence
gptkb:software_framework
gptkb:Deep_Learning
|
|
gptkbp:training
|
Stochastic Gradient Descent
Backpropagation Through Time
|