Part 12

PArt 10: Dense

PArt 11: Tensorflow Playground

Part 9: Sequential vs Functional NN

Part 8: L1 (Lasso Regression) L2 (Ridge Regression) Elastic Net Regression

Part 7: Various Hyperparameters for Various Layers

PArt 6: Optimizers: - SGD - RMSprop (for Regression) - Adam (for Classification) Regression Loss Model (or Accuracy Metric): - MSE - MAE Categorical Loss Model: - Categorial_crossentropy - Sparse_categorical_crossentropy

Part 5: Activation Functions: Sigmoid / Relu / Tanh

Part 4: Epochs and Batch Size

Part 3: Hyperparameters Available: - Learning Rate - Activiation Function - Regularization - Regularization Rate - Batch Size - Ratio of Training to Test Data - Number of Hidden Layers - Features of Data Set

Part 2: Forward + Backward Propagation

PArt 1: Basic Perceptron Model