|
gptkbp:instance_of
|
gptkb:Management
gptkb:research
gptkb:book
gptkb:machine_learning
|
|
gptkbp:analyzes
|
Decision boundary
Support vectors
|
|
gptkbp:anatomy
|
gptkb:Yes
|
|
gptkbp:author
|
gptkb:Yoshua_Bengio
gptkb:Aaron_Courville
gptkb:Ian_Goodfellow
|
|
gptkbp:available_at
|
gptkb:Amazon
gptkb:Barnes_&_Noble
MIT Press Website
|
|
gptkbp:based_on
|
Statistical Learning Theory
|
|
gptkbp:business_model
|
gptkb:Autonomous_Weapons
gptkb:security
Surveillance
Job Displacement
Algorithmic Bias
|
|
gptkbp:can_be_combined_with
|
Feature selection techniques
Dimensionality reduction techniques
|
|
gptkbp:can_be_extended_by
|
Support Vector Regression
One-class SVM
|
|
gptkbp:can_handle
|
Non-linear data
|
|
gptkbp:challenges
|
Data Quality
Overfitting
Underfitting
Interpretability
Bias-Variance Tradeoff
|
|
gptkbp:contains
|
gptkb:Yes
|
|
gptkbp:contains_figures
|
gptkb:Yes
|
|
gptkbp:developed_by
|
gptkb:Alexey_Chervonenkis
gptkb:Vladimir_Vapnik
|
|
gptkbp:evaluates
|
Accuracy
F1 Score
Precision
Recall
ROC AUC
|
|
gptkbp:features_works_by
|
Finding hyperplane
|
|
gptkbp:first_edition
|
First Edition
|
|
gptkbp:format
|
gptkb:e_Book
Hardcover
Paperback
|
|
gptkbp:has_applications_in
|
gptkb:Computer_Vision
gptkb:Natural_Language_Processing
gptkb:Data_Analytics
Recommendation Systems
|
|
gptkbp:has_function
|
C (Regularization parameter)
Gamma (Kernel coefficient)
|
|
gptkbp:has_method
|
gptkb:Support_Vector_Machines
gptkb:Decision_Trees
gptkb:Random_Forests
gptkb:neural_networks
gptkb:machine_learning
Supervised Learning
Unsupervised Learning
K-Means Clustering
Gradient Boosting
|
|
gptkbp:has_weapon
|
gptkb:Tensor_Flow
gptkb:Apache_Spark
gptkb:Keras
gptkb:Py_Torch
gptkb:Scikit-learn
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
machine learning
|
|
https://www.w3.org/2000/01/rdf-schema#subClassOf
|
gptkb:Artificial_Intelligence
|
|
gptkbp:influenced_by
|
gptkb:neural_networks
Optimization Techniques
Statistical Learning Theory
|
|
gptkbp:is_applied_in
|
gptkb:citizens
|
|
gptkbp:is_challenged_by
|
Large datasets
High dimensionality
Imbalanced classes
|
|
gptkbp:is_cited_in
|
Theses
Numerous academic papers
Research projects
|
|
gptkbp:is_evaluated_by
|
Accuracy
F1 Score
Precision
Recall
|
|
gptkbp:is_implemented_in
|
gptkb:Tensor_Flow
gptkb:MATLAB
gptkb:R
gptkb:LIBSVM
gptkb:Scikit-learn
|
|
gptkbp:is_popular_in
|
Bioinformatics
Text classification
Image recognition
Handwriting recognition
|
|
gptkbp:is_related_to
|
gptkb:Decision_Trees
gptkb:Random_Forests
gptkb:neural_networks
Ensemble Methods
|
|
gptkbp:is_used_in
|
gptkb:advertising
gptkb:World_State
Finance
Healthcare
Sentiment analysis
Speech recognition
Fraud detection
Customer segmentation
Face detection
Image classification
Object detection
Stock market prediction
Bioinformatics classification
|
|
gptkbp:isbn
|
978-0262035613
|
|
gptkbp:language
|
English
|
|
gptkbp:page_count
|
800
|
|
gptkbp:provides_information_on
|
gptkb:UCI_Machine_Learning_Repository
gptkb:Image_Net
gptkb:CIFAR-10
gptkb:MNIST
Kaggle Datasets
|
|
gptkbp:published_year
|
gptkb:2016
|
|
gptkbp:publisher
|
gptkb:MIT_Press
|
|
gptkbp:related_to
|
gptkb:Artificial_Intelligence
gptkb:Data_Science
Statistics
|
|
gptkbp:requires
|
Feature scaling
|
|
gptkbp:reviews
|
Highly regarded in the field
|
|
gptkbp:sensitivity
|
gptkb:Outliers
|
|
gptkbp:subject
|
gptkb:machine_learning
|
|
gptkbp:table_of_contents
|
gptkb:Deep_Learning
Introduction
Linear Algebra
Unsupervised Learning
Conclusion
Numerical Computation
Applications
Machine Learning Basics
Probability and Information Theory
|
|
gptkbp:target_audience
|
gptkb:students
gptkb:researchers
Practitioners
|
|
gptkbp:translated_into
|
gptkb:Japanese
gptkb:Korean
gptkb:Spanish
gptkb:Russian
Chinese
|
|
gptkbp:trends
|
gptkb:Federated_Learning
gptkb:Quantum_Computing
gptkb:stage_adaptation
gptkb:machine_learning
gptkb:AI_technology
|
|
gptkbp:used_for
|
gptkb:Regression
Classification
|
|
gptkbp:uses
|
Kernel Trick
|
|
gptkbp:bfsParent
|
gptkb:Massachusetts_Institute_of_Technology
|
|
gptkbp:bfsLayer
|
2
|