Statements (60)
Predicate | Object |
---|---|
gptkbp:instance_of |
gptkb:microprocessor
|
gptkbp:bfsLayer |
5
|
gptkbp:bfsParent |
gptkb:Long_Short-Term_Memory_Network
|
gptkbp:applies_to |
traffic prediction
weather forecasting video analysis |
gptkbp:can_be_used_with |
Convolutional Neural Networks and LST Ms
|
gptkbp:content_type |
Convolutional Layer
LSTM Layer |
gptkbp:developed_by |
Shengshi Liu
|
gptkbp:first_introduced |
gptkb:2015
|
gptkbp:has_programs |
gptkb:robot
healthcare autonomous driving |
https://www.w3.org/2000/01/rdf-schema#label |
Conv LSTM
|
gptkbp:is_different_from |
Standard LSTM
|
gptkbp:is_evaluated_by |
accuracy metrics
real-time data F1 score loss functions precision and recall benchmark datasets synthetic datasets real-world tasks |
gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
gptkbp:is_known_for |
handling spatial and temporal dependencies
|
gptkbp:is_optimized_for |
gptkb:Adam_optimizer
SGD |
gptkbp:is_part_of |
gptkb:Model
gptkb:Research_Institute data science projects machine learning applications time series analysis deep learning frameworks computer vision tasks sequence modeling techniques |
gptkbp:is_popular_in |
deep learning community
|
gptkbp:is_related_to |
gptkb:television_channel
gptkb:Recurrent_Neural_Networks Temporal Convolutional Networks |
gptkbp:is_similar_to |
3 D Convolutional Networks
|
gptkbp:is_used_by |
gptkb:physicist
industry practitioners |
gptkbp:is_used_for |
sequence prediction
forecasting tasks spatiotemporal data prediction |
gptkbp:is_used_in |
gptkb:sports_team
gptkb:academic_research environmental monitoring financial forecasting commercial applications video prediction image captioning action recognition |
gptkbp:requires |
GPU for training
large datasets for training |
gptkbp:training |
overfitting
Backpropagation Through Time vanishing gradients |