scikit-learn ゼミ

http://scikit-learn.org/stable/index.html

　　　　　　　　日時　　　　　　　　　　 内容 スライドのファイル 補足資料など 発表者
 4月24日 1.Supervised Learning
1.1. Generalized Linear Models
1.1.1. Ordinary Least Squares
1.1.1.1. Ordinary Least Squares Complexity
1.1.2. Ridge Regression
1.1.2.1. Ridge Complexity
1.1.2.2. Setting the regularization parameter: generalized Cross-Validation		  sklearn-shinnou-0424.pdf   新納
 5月8日 1.1.3. Lasso
1.1.3.1. Setting regularization parameter
1.1.3.1.1. Using cross-validation
1.1.3.1.2. Information-criteria based model selection		  sklearn-kunii-0508.pdf   國井
  1.1.4. Elastic Net  sklearn-kikuchi-0508.pdf   菊池
1.1.5. Multi-task Lasso  sklearn-onodera-0508.pdf   小野寺 
 5月15日 1.1.6. Least Angle Regression  sklearn-xiao-0515.pdf   Xiao
  1.1.7. LARS Lasso
1.1.7.1. Mathematical formulation		  sklearn-kouno-0515.pdf   河野
1.1.8. Orthogonal Matching Pursuit (OMP)  sklearn-nagata-0515.pdf   永田
 5月22日 1.1.9. Bayesian Regression
1.1.9.1. Bayesian Ridge Regression
1.1.9.2. Automatic Relevance Determination - ARD		  sklearn-shinnou-0522.pdf   新納
  1.1.10. Logistic regression  sklearn-kunii-0522.pdf   國井
  1.1.11. Stochastic Gradient Descent - SGD  sklearn-kikuchi-0522.pdf   菊池
 5月29日 1.1.12. Perceptron  sklearn-onodera-0529.pdf   小野寺
  1.1.13. Passive Aggressive Algorithms sklearn-xiao-0529.pdf   Xiao
1.2. Support Vector Machines
1.2.1. Classification
1.2.1.1. Multi-class classification
1.2.1.2. Scores and probabilities
1.2.1.3. Unbalanced problems		  sklearn-kouno-0529.pdf   河野
6月5日 1.2.2. Regression  sklearn-nagata-0605.pdf   永田
1.2.3. Density estimation, novelty detection  sklearn-shinnou-0605.pdf   新納
1.2.4. Complexity  sklearn-kunii-0605.pdf   國井
1.2.5. Tips on Practical Use  sklearn-kikuchi-0605.pdf   菊池
6月12日 1.2.6. Kernel functions
1.2.6.1. Custom Kernels
1.2.6.1.1. Using Python functions as kernels
1.2.6.1.2. Using the Gram matrix
1.2.6.1.3. Parameters of the RBF Kernel		  sklearn-onodera-0612.pdf   小野寺
1.2.7. Mathematical formulation
1.2.7.1. SVC
1.2.7.2. NuSVC		 sklearn-xiao-0612.pdf   Xiao
1.2.8. Implementation details sklearn-kouno-0612.pdf   河野
1.3. Stochastic Gradient Descent
1.3.1. Classification		 sklearn-shinnou-0612.pdf   永田→新納
6月26日 1.3.2. Regression sklearn-shinnou-0626.pdf   新納
1.3.3. Stochastic Gradient Descent for sparse data     國井
1.3.4. Complexity     菊池
1.3.5. Tips on Practical Use sklearn-onodera-0626.pdf   小野寺
10月14日 1.3.6. Mathematical formulation
1.3.6.1. SGD		 sklearn-xiao-1014.pptx   Xiao
1.3.7. Implementation details sklearn-kouno-1014.pdf   河野
1.4. Nearest Neighbors
1.4.1. Unsupervised Nearest Neighbors
1.4.1.1. Finding the Nearest Neighbors
1.4.1.2. KDTree and BallTree Classes		 sklearn-nagata-1014.pdf   永田
1.4.2. Nearest Neighbors Classification sklearn-shinnou-1014.pdf   新納
10月21日 1.4.3. Nearest Neighbors Regression sklearn-kunii-1021.pdf   國井
1.4.4. Nearest Neighbor Algorithms
1.4.4.1. Brute Force
1.4.4.2. K-D Tree
1.4.4.3. Ball Tree
1.4.4.4. Choice of Nearest Neighbors Algorithm
1.4.4.5. Effect of leaf_size		 sklearn-kikuchi-1021.pdf   菊池
1.4.5. Nearest Centroid Classifier
1.4.5.1. Nearest Shrunken Centroid		 sklearn-onodera-1021.pdf   小野寺
1.5. Gaussian Processes
1.5.1. Examples
1.5.1.1. An introductory regression example
1.5.1.2. Fitting Noisy Data		 sklearn-xiao-1021.pptx   Xiao
10月28日 1.5.2. Mathematical formulation
1.5.2.1. The initial assumption
1.5.2.2. The best linear unbiased prediction (BLUP)
1.5.2.3. The empirical best linear unbiased predictor (EBLUP)		 sklearn-kouno-1028.pdf   河野
1.5.3. Correlation Models sklearn-nagata-1028.pdf   永田
1.5.4. Regression Models sklearn-shinnou-1028.pdf   新納
1.5.5. Implementation details sklearn-kunii-1028.pdf   國井
11月4日 1.6. Cross decomposition sklearn-kikuchi-1104.pdf   菊池
1.7. Naive Bayes
1.7.1. Gaussian Naive Bayes		 sklearn-onodera-1104.pdf   小野寺
1.7.2. Multinomial Naive Bayes sklearn-xiao-1104.pptx   Xiao
1.7.3. Bernoulli Naive Bayes sklearn-kouno-1104.pdf   河野
1.7.4. Out-of-core naive Bayes model fitting sklearn-nagata-1104.pdf   永田
11月11日 1.8. Decision Trees
1.8.1. Classification		 sklearn-shinnou-1111.pdf   新納
1.8.2. Regression sklearn-kunii-1111.pdf   國井
1.8.3. Multi-output problems sklearn-kikuchi-1111.pdf   菊池
1.8.4. Complexity sklearn-onodera-1111.pdf   小野寺
1.8.5. Tips on practical use sklearn-xiao-1111.pdf   Xiao
1.8.6. Tree algorithms: ID3, C4.5, C5.0 and CART sklearn-kouno-1111.pdf   河野
1.8.7. Mathematical formulation
1.8.7.1. Classification criteria
1.8.7.2. Regression criteria		 sklearn-nagata-1111.pdf   永田
 11月21日 1.9. Ensemble methods
1.9.1. Forests of randomized trees
1.9.1.1. Random Forests
1.9.1.2. Extremely Randomized Trees
1.9.1.3. Parameters
1.9.1.4. Parallelization
1.9.1.5. Feature importance evaluation
1.9.1.6. Totally Random Trees Embedding		 sklearn-shinnou-1121.pdf   新納
  1.9.2. AdaBoost
1.9.2.1. Usage		 sklearn-kunii-1121.pdf   國井
  1.9.3. Gradient Tree Boosting
1.9.3.1. Classification
1.9.3.2. Regression
1.9.3.3. Mathematical formulation
1.9.3.3.1. Loss Functions
1.9.3.4. Regularization
1.9.3.4.1. Shrinkage
1.9.3.4.2. Subsampling
1.9.3.5. Interpretation
1.9.3.5.1. Feature importance
1.9.3.5.2. Partial dependence		 sklearn-kikuchi-1121.pdf   菊池
 11月25日 1.10. Multiclass and multilabel algorithms
1.10.1. Multilabel classification format		 sklearn-onodera-1125.pdf   小野寺
  1.10.2. One-Vs-The-Rest
1.10.2.1. Multiclass learning
1.10.2.2. Multilabel learning		 sklearn-xiao-1125.pdf   Xiao
  1.10.3. One-Vs-One
1.10.3.1. Multiclass learning		 sklearn-kouno-1125.pdf   河野
  1.10.4. Error-Correcting Output-Codes
1.10.4.1. Multiclass learning		 sklearn-nagata-1125.pdf   永田
 12月2日 1.11. Feature selection
1.11.1. Removing features with low variance
1.11.2. Univariate feature selection 		sklearn-shinnou-1202.pdf   新納
  1.11.3. Recursive feature elimination     國井
  1.11.4. L1-based feature selection
1.11.4.1. Selecting non-zero coefficients
1.11.4.2. Randomized sparse models		 sklearn-kikuchi-1202.pdf   菊池
  1.11.5. Tree-based feature selection     小野寺
  1.11.6. Feature selection as part of a pipeline sklearn-xiao-1202.pdf   Xiao
 12月5日 1.12. Semi-Supervised
1.12.1. Label Propagation		     河野
  1.13. Linear and quadratic discriminant analysis
1.13.1. Dimensionality reduction using LDA		     永田
  1.13.2. Mathematical Idea sklearn-shinnou-1205.pdf   新納
  1.14. Isotonic regression     國井
 81 2. Unsupervised Learning
2.1. Gaussian mixture models
2.1.1. GMM classifier
2.1.1.1. Pros and cons of class GMM: expectation-maximization inference
2.1.1.1.1. Pros
2.1.1.1.2. Cons		     菊池
  2.1.1.2. Selecting the number of components in a classical GMM
2.1.1.3. Estimation algorithm Expectation-maximization		     小野寺
  2.1.2. VBGMM classifier: variational Gaussian mixtures
2.1.2.1. Pros and cons of class VBGMM: variational inference
2.1.2.1.1. Pros
2.1.2.1.2. Cons
2.1.2.2. Estimation algorithm: variational inference		     Xiao
  2.1.3. DPGMM classifier: Infinite Gaussian mixtures
2.1.3.1. Pros and cons of class DPGMM: Diriclet process mixture model
2.1.3.1.1. Pros
2.1.3.1.2. Cons
2.1.3.2. The Dirichlet Process		     河野
 82 2.2. Manifold learning
2.2.1. Introduction		     永田
2.2.2. Isomap
2.2.2.1. Complexity		 新納
  2.2.3. Locally Linear Embedding
2.2.3.1. Complexity		     國井
2.2.4. Modified Locally Linear Embedding
2.2.4.1. Complexity		     菊池
  2.2.5. Hessian Eigenmapping
2.2.5.1. Complexity		     小野寺
 83 2.2.6. Spectral Embedding
2.2.6.1. Complexity		     Xiao
  2.2.7. Local Tangent Space Alignment
2.2.7.1. Complexity		     河野
  2.2.8. Multi-dimensional Scaling (MDS)
2.2.8.1. Metric MDS
2.2.8.2. Nonmetric MDS		     永田
  2.2.9. Tips on practical use     新納
 84 2.3. Clustering
2.3.1. Overview of clustering methods		     國井
  2.3.2. K-means
2.3.2.1. Mini Batch K-Means		     菊池
2.3.3. Affinity Propagation     小野寺
  2.3.4. Mean Shift     Xiao
  2.3.5. Spectral clustering
2.3.5.1. Different label assignment strategies		     河野
 85 2.3.6. Hierarchical clustering
2.3.6.1. Adding connectivity constraints		     永田
  2.3.7. DBSCAN     新納
  2.3.8. Clustering performance evaluation
2.3.8.1. Inertia
2.3.8.1.1. Presentation and usage
2.3.8.1.2. Advantages
2.3.8.1.3. Drawbacks
2.3.8.2. Adjusted Rand index
2.3.8.2.1. Presentation and usage
2.3.8.2.2. Advantages
2.3.8.2.3. Drawbacks
2.3.8.2.4. Mathematical formulation
2.3.8.3. Mutual Information based scores
2.3.8.3.1. Presentation and usage
2.3.8.3.2. Advantages
2.3.8.3.3. Drawbacks
2.3.8.3.4. Mathematical formulation
2.3.8.4. Homogeneity, completeness and V-measure
2.3.8.4.1. Presentation and usage
2.3.8.4.2. Advantages
2.3.8.4.3. Drawbacks
2.3.8.4.4. Mathematical formulation
2.3.8.5. Silhouette Coefficient
2.3.8.5.1. Presentation and usage
2.3.8.5.2. Advantages
2.3.8.5.3. Drawbacks		     國井
 86 2.4. Biclustering
2.4.1. Spectral Co-Clustering
2.4.1.1. Mathematical formulation		     菊池
 87 2.4.2. Spectral Biclustering
2.4.2.1. Mathematical formulation		     小野寺
 88 2.4.3. Biclustering evaluation     Xiao
 89 2.5. Decomposing signals in components (matrix factorization problems)
2.5.1. Principal component analysis (PCA)
2.5.1.1. Exact PCA and probabilistic interpretation
2.5.1.2. Approximate PCA
2.5.1.3. Kernel PCA
2.5.1.4. Sparse principal components analysis (SparsePCA and MiniBatchSparsePCA)		     河野
 90 2.5.2. Truncated singular value decomposition and latent semantic analysis     永田
 91 2.5.3. Dictionary Learning
2.5.3.1. Sparse coding with a precomputed dictionary
2.5.3.2. Generic dictionary learning
2.5.3.3. Mini-batch dictionary learning		     新納
 92 2.5.4. Factor Analysis     國井
 93 2.5.5. Independent component analysis (ICA)     菊池
 94 2.5.6. Non-negative matrix factorization (NMF or NNMF)     小野寺
 95 2.6. Covariance estimation
2.6.1. Empirical covariance		     Xiao
 96 2.6.2. Shrunk Covariance
2.6.2.1. Basic shrinkage
2.6.2.2. Ledoit-Wolf shrinkage
2.6.2.3. Oracle Approximating Shrinkage		     河野
 97 2.6.3. Sparse inverse covariance     永田
 98 2.6.4. Robust Covariance Estimation
2.6.4.1. Minimum Covariance Determinant		     新納
 99 2.7. Novelty and Outlier Detection
2.7.1. Novelty Detection		     國井
 100 2.7.2. Outlier Detection
2.7.2.1. Fitting an elliptic envelop
2.7.2.2. One-class SVM versus elliptic envelop		     菊池
 101 2.8. Hidden Markov Models
2.8.1. Using HMM
2.8.1.1. Building HMM and generating samples
2.8.1.2. Training HMM parameters and inferring the hidden states
2.8.1.3. Implementing HMMs with custom emission probabilities		     小野寺
 102 2.9. Density Estimation
2.9.1. Density Estimation: Histograms		     Xiao
 103 2.9.2. Kernel Density Estimation     河野
 104 2.10. Neural network models (unsupervised)
2.10.1. Restricted Boltzmann machines
2.10.1.1. Graphical model and parametrization
2.10.1.2. Bernoulli Restricted Boltzmann machines
2.10.1.3. Stochastic Maximum Likelihood learning		     永田
 105 3. Model selection and evaluation
3.1. Cross-validation: evaluating estimator performance
3.1.1. Computing cross-validated metrics		     新納
 106 3.1.2. Cross validation iterators
3.1.2.1. K-fold
3.1.2.2. Stratified k-fold
3.1.2.3. Leave-One-Out - LOO
3.1.2.4. Leave-P-Out - LPO
3.1.2.5. Leave-One-Label-Out - LOLO
3.1.2.6. Leave-P-Label-Out
3.1.2.7. Random permutations cross-validation a.k.a. Shuffle & Split
3.1.2.8. See also
3.1.2.9. Bootstrapping cross-validation		     國井
 107 3.1.3. Cross validation and model selection     菊池
 108 3.2. Grid Search: Searching for estimator parameters
3.2.1. Exhaustive Grid Search
3.2.1.1. Scoring functions for parameter search		     小野寺
109 3.2.2. Randomized Parameter Optimization Xiao
 110 3.2.3. Alternatives to brute force parameter search
3.2.3.1. Model specific cross-validation
3.2.3.1.1. sklearn.linear_model.RidgeCV
3.2.3.1.2. sklearn.linear_model.RidgeClassifierCV
3.2.3.1.3. sklearn.linear_model.LarsCV
3.2.3.1.4. sklearn.linear_model.LassoLarsCV
3.2.3.1.5. sklearn.linear_model.LassoCV
3.2.3.1.6. sklearn.linear_model.ElasticNetCV
3.2.3.2. Information Criterion
3.2.3.2.1. sklearn.linear_model.LassoLarsIC
3.2.3.3. Out of Bag Estimates
3.2.3.3.1. sklearn.ensemble.RandomForestClassifier
3.2.3.3.2. sklearn.ensemble.RandomForestRegressor
3.2.3.3.3. sklearn.ensemble.ExtraTreesClassifier
3.2.3.3.4. sklearn.ensemble.ExtraTreesRegressor
3.2.3.3.5. sklearn.ensemble.GradientBoostingClassifier
3.2.3.3.6. sklearn.ensemble.GradientBoostingRegressor		     河野
 111 3.3. Pipeline: chaining estimators
3.3.1. Usage		     永田
 112 3.3.2. Notes     新納
 113 3.4. FeatureUnion: Combining feature extractors
3.4.1. Usage		     國井
 114 3.5. Model evaluation: quantifying the quality of predictions
3.5.1. The scoring parameter: defining model evaluation rules
3.5.1.1. Common cases: predefined values
3.5.1.2. Defining your scoring strategy from score functions
3.5.1.3. Implementing your own scoring object		     菊池
 115 3.5.2. Function for prediction-error metrics
3.5.2.1. Classification metrics
3.5.2.1.1. Accuracy score
3.5.2.1.2. Average precision score
3.5.2.1.3. Confusion matrix
3.5.2.1.4. Classification report
3.5.2.1.5. Hamming loss
3.5.2.1.6. Jaccard similarity coefficient score
3.5.2.1.7. Precision, recall and F-measures
3.5.2.1.7.1. Binary classification
3.5.2.1.7.2. Multiclass and multilabel classification
3.5.2.1.8. Hinge loss
3.5.2.1.9. Log loss
3.5.2.1.10. Matthews correlation coefficient
3.5.2.1.11. Receiver operating characteristic (ROC)
3.5.2.1.12. Zero one loss
3.5.2.2. Regression metrics
3.5.2.2.1. Explained variance score
3.5.2.2.2. Mean absolute error
3.5.2.2.3. Mean squared error
3.5.2.2.4. Rﾂｲ score, the coefficient of determination		     小野寺
 116 3.5.3. Clustering metrics     Xiao
 117 3.5.4. Biclustering metrics
3.5.4.1. Clustering metrics		     河野
 118 3.5.5. Dummy estimators     永田
 119 4.1. Feature extraction
4.1.1. Loading features from dicts		     新納
 120 4.1.2. Feature hashing     國井
 121 4.1.3. Text feature extraction     菊池
 122 4.1.4. Image feature extraction     小野寺
 123 4.2. Preprocessing data
4.2.1. Standardization, or mean removal and variance scaling		     Xiao
 124 4.2.2. Normalization     河野
 125 4.2.3. Binarization     永田
 126 4.2.4. Encoding categorical features     新納
 127 4.2.5. Label preprocessing     國井
 128 4.2.6. Imputation of missing values     菊池
 129 4.3. Kernel Approximation
4.3.1. Nystroem Method for Kernel Approximation		     小野寺
 130 4.3.2. Radial Basis Function Kernel     Xiao
 131 4.3.3. Additive Chi Squared Kernel     河野
 132 4.3.4. Skewed Chi Squared Kernel     永田
 133 4.3.5. Mathematical Details     新納
 134 4.4. Random Projection
4.4.1. The Johnson-Lindenstrauss lemma		     國井
 135 4.4.2. Gaussian random projection     菊池
 136 4.4.3. Sparse random projection     小野寺
 137 4.5. Pairwise metrics, Affinities and Kernels
4.5.1. Cosine similarity		     Xiao
 138 4.5.2. Chi Squared Kernel     河野
 139 5. Dataset loading utilities
5.1. General dataset API		     永田
 140 5.2. Toy datasets     新納→永田
 141 5.3. Sample images     國井
 142 5.4. Sample generators     菊池
 143 5.5. Datasets in svmlight / libsvm format     小野寺
 144 5.6. The Olivetti faces dataset     Xiao
 145 5.7. The 20 newsgroups text dataset
5.7.1. Usage		     河野
 146 5.7.2. Converting text to vectors     永田
 147 5.7.3. Filtering text for more realistic training     新納→永田
 148 5.8. Downloading datasets from the mldata.org repository     國井
 149 5.9. The Labeled Faces in the Wild face recognition dataset
5.9.1. Usage		     菊池
 150 5.9.2. Examples     小野寺
 151 5.10. Forest covertypes     Xiao