44) Ordinal Data MappingA technique where each label is mapped to a number representing its order among others Nov 7, 2023, 8:07 PM Navid
45) PCA and T-SNEDimensionality reduction techniques with PCA for linear and T-SNE for non-linear dimensionality reduction Nov 7, 2023, 8:07 PM Navid
53) Word EmbeddingRepresents words in such a way that similar words are close to each other in the embedding space Nov 7, 2023, 8:07 PM Navid
52) TF-IDFGives more importance to words that are unique to the document Nov 7, 2023, 8:07 PM Navid
63) Training vs Testing DistributionModels should not be trained on one distribution of data and tested on a completely different one to avoid poor performance Nov 7, 2023, 8:07 PM Navid
62) Feature-Feature CorrelationStrongly correlated features should be removed to prevent overemphasis and multicollinearity Nov 7, 2023, 8:07 PM Navid
64) High BiasIndicates underfitting where the model is too simple and does not capture the complexity of the data Nov 7, 2023, 8:07 PM Navid
73) Softmax Activation FunctionUsed in the output layer for multi-class classification to create a probability distribution among classes Nov 7, 2023, 8:07 PM Navid
75) L1 RegularizationA regularization method that performs feature selection by allowing some feature weights to shrink to zero Nov 7, 2023, 8:07 PM Navid
42) Bubble ChartVisualizes three-dimensional data in a two-dimensional diagram Nov 7, 2023, 8:07 PM Navid
41) Tree MapVisualizes data in a hierarchical diagram Nov 7, 2023, 8:07 PM Navid
50) Amazon Ground TruthA service within Amazon Sagemaker that labels datasets for use in machine learning with options for Mechanical Turk private workforce or vendors Nov 7, 2023, 8:07 PM Navid
51) Bag of WordsA matrix representation to describe the number of words within the text Nov 7, 2023, 8:07 PM Navid
59) Machine LearningA field of AI that uses statistical techniques to give computer systems the ability to learn from data Nov 7, 2023, 8:07 PM Navid
60) Overfitting PreventionTechniques include data augmentation Nov 7, 2023, 8:07 PM Navid
61) Data Augmentation in ImagesInvolves flipping Nov 7, 2023, 8:07 PM Navid
71) Xavier and Normalized XavierWeight initialization techniques to help in training neural networks Nov 7, 2023, 8:07 PM Navid
70) BoostingTrains classifiers sequentially with each considering the previous one Nov 7, 2023, 8:07 PM Navid
79) Batch Size in TrainingSmall batch sizes tend to avoid getting stuck in local minima Nov 7, 2023, 8:07 PM Navid
80) Learning RateA large learning rate can overshoot the solution Nov 7, 2023, 8:07 PM Navid