|
gptkbp:instance_of
|
gptkb:machine_learning
|
|
gptkbp:analyzes
|
gptkb:PCA
t-SNE
|
|
gptkbp:can_be_combined_with
|
convolutional neural networks
recurrent neural networks
|
|
gptkbp:can_be_fine_tuned_using
|
backpropagation
|
|
gptkbp:can_be_regularized_using
|
L2 regularization
dropout
|
|
gptkbp:can_be_used_for
|
dimensionality reduction
|
|
gptkbp:composed_of
|
multiple layers
|
|
gptkbp:developed_by
|
gptkb:Geoffrey_R._Hinton
|
|
gptkbp:first_introduced
|
gptkb:2006
|
|
gptkbp:has_applications_in
|
gptkb:robotics
finance
bioinformatics
|
|
gptkbp:has_limitations
|
training time
interpretability
|
|
gptkbp:has_research_focus
|
transfer learning
semi-supervised learning
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Deep Belief Networks
|
|
gptkbp:improves
|
feature extraction
|
|
gptkbp:is_applied_in
|
image recognition
natural language processing
speech recognition
|
|
gptkbp:is_challenged_by
|
overfitting
adversarial attacks
vanishing gradients
|
|
gptkbp:is_different_from
|
traditional neural networks
|
|
gptkbp:is_evaluated_by
|
F1 score
ROC AUC
accuracy
cross-validation
benchmark datasets
|
|
gptkbp:is_implemented_in
|
gptkb:Tensor_Flow
gptkb:Python
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:is_influenced_by
|
biological neural networks
|
|
gptkbp:is_optimized_for
|
gradient descent
|
|
gptkbp:is_part_of
|
gptkb:Artificial_Intelligence
gptkb:neural_networks
|
|
gptkbp:is_popular_in
|
gptkb:scientific_community
industry applications
|
|
gptkbp:is_similar_to
|
autoencoders
variational autoencoders
|
|
gptkbp:is_used_in
|
recommendation systems
self-driving cars
game AI
|
|
gptkbp:related_to
|
deep learning
|
|
gptkbp:requires
|
large datasets
|
|
gptkbp:training
|
contrastive divergence
|
|
gptkbp:used_for
|
unsupervised learning
|
|
gptkbp:utilizes
|
restricted Boltzmann machines
|
|
gptkbp:bfsParent
|
gptkb:Jürgen_Schmidhuber
gptkb:Geoffrey_R._Hinton
|
|
gptkbp:bfsLayer
|
3
|