Distillation are widely different learning techniques. While data augmentation is concerned with samples and labels, distillation transfers knowledge from a large model or ensemble of models to smaller models. The looking at each example and assigning them a label that they believe describes it best. The assigned labels are subjective to the perception of their labelers. For example, a human labeler might perceive the that can potentially confuse the human labelers to choose a 1 or a 7 as the target label. Obtaining labels in many cases requires significant human involvement, and for that reason can be expensive and slow

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 6.6 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 6.7 Iteration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 7.2 Advanced indexing with labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76 7.3 Index objects series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 6.6 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 6.7 Iteration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 7.2 Advanced indexing with labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76 7.3 Index objects series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 217 ii 9.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 222 9.8 Iteration . . . . . . . . . . . . . . . . . . . . . . . 294 10.24 Setting index metadata (name(s), levels, labels) . . . . . . . . . . . . . . . . . . . . . . . . 311 10.25 Adding an index to an existing DataFrame series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 352 10.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 358 10.8 Iteration series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled Automatic and explicit data alignment: objects can be explicitly aligned to a set of labels, or the user can simply ignore the labels and let Series, DataFrame, etc. automatically align the data for you in computations

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 6.6 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61 i 6.7 Iteration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75 7.2 Advanced indexing with labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82 7.3 Index objects series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 189 9.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 195 ii 9.8 Iteration . . . . . . . . . . . . . . . . . . . . . . 267 10.24 Setting index metadata (name(s), levels, labels) . . . . . . . . . . . . . . . . . . . . . . . . 279 10.25 Adding an index to an existing DataFrame series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 287 9.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292 9.8 Iteration . series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled Automatic and explicit data alignment: objects can be explicitly aligned to a set of labels, or the user can simply ignore the labels and let Series, DataFrame, etc. automatically align the data for you in computations

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279 9.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284 9.8 Iteration . series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled Automatic and explicit data alignment: objects can be explicitly aligned to a set of labels, or the user can simply ignore the labels and let Series, DataFrame, etc. automatically align the data for you in computations

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145 8.7 Reindexing and altering labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148 8.8 Iteration . series data. • Arbitrary matrix data (homogeneously typed or heterogeneous) with row and column labels • Any other form of observational / statistical data sets. The data actually need not be labeled Automatic and explicit data alignment: objects can be explicitly aligned to a set of labels, or the user can simply ignore the labels and let Series, DataFrame, etc. automatically align the data for you in computations