Statements (63)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:neural_networks
|
| gptkbp:adapted_into |
multi-modal learning
|
| gptkbp:analyzes |
t-SNE
|
| gptkbp:are_effective_for |
few-shot learning
|
| gptkbp:can_be_fine-tuned_with |
transfer learning
|
| gptkbp:can_be_used_for |
gptkb:virtual_reality
gptkb:robotics language translation augmented reality data visualization question answering time series analysis data mining predictive modeling sentiment analysis customer segmentation data augmentation data compression fraud detection self-driving cars social network analysis data clustering spam detection feature extraction anomaly detection chatbot development knowledge discovery text classification text similarity game AI image similarity metric learning video similarity |
| gptkbp:can_be_used_in |
recommendation systems
medical image analysis |
| gptkbp:can_be_used_to |
detect anomalies
match pairs of data |
| gptkbp:can_handle |
variable input sizes
|
| gptkbp:compare |
two input samples
|
| gptkbp:consists_of |
two identical subnetworks
|
| gptkbp:developed_by |
gptkb:one-shot_learning
|
| gptkbp:first_introduced |
Bromley et al.
|
| https://www.w3.org/2000/01/rdf-schema#label |
Siamese networks
|
| gptkbp:input_output |
similarity score
|
| gptkbp:is_applied_in |
natural language processing
biometric identification |
| gptkbp:is_designed_to |
learn embeddings
|
| gptkbp:is_evaluated_by |
accuracy metrics
|
| gptkbp:is_implemented_in |
gptkb:Tensor_Flow
gptkb:Py_Torch convolutional layers recurrent layers |
| gptkbp:is_popular_in |
computer vision
|
| gptkbp:is_related_to |
twin networks
|
| gptkbp:is_trained_in |
labeled datasets
contrastive loss triplet loss |
| gptkbp:used_in |
image recognition
signature verification face verification |
| gptkbp:bfsParent |
gptkb:Few-Shot_Learning
gptkb:one-shot_learning |
| gptkbp:bfsLayer |
6
|