coursera-advanced-learning-algorithms-2022-6

1_neural-networks\ 1_neural-networks-intuition\ 0:00 1_welcome 2:53 2_neurons-and-the-brain 13:45 3_demand-prediction 30:08 4_example-recognizing-images 2_neural-network-model\ 36:43 1_neural-network-layer 46:32 2_more-complex-neural-networks 53:51 3_inference-making-predictions-forward-propagation 3_tensorflow-implementation\ 59:14 1_inference-in-code 1:06:26 2_data-in-tensorflow 1:17:45 3_building-a-neural-network 4_neural-network-implementation-in-python\ 1:26:06 1_forward-prop-in-a-single-layer 1:31:13 2_general-implementation-of-forward-propagation 5_speculations-on-artificial-general-intelligence-agi\ 1:39:05 1_is-there-a-path-to-agi 6_vectorization-optional\ 1:49:39 1_how-neural-networks-are-implemented-efficiently 1:54:02 2_matrix-multiplication 2:03:29 3_matrix-multiplication-rules 2:13:02 4_matrix-multiplication-code 2_neural-network-training\ 1_neural-network-training\ 2:19:43 1_tensorflow-implementation 2:23:20 2_training-details 2_activation-functions\ 2:37:00 1_alternatives-to-the-sigmoid-activation 2:42:30 2_choosing-activation-functions 2:50:54 3_why-do-we-need-activation-functions 3_multiclass-classification\ 2:56:25 1_multiclass 2:59:53 2_softmax 3:11:26 3_neural-network-with-softmax-output 3:18:50 4_improved-implementation-of-softmax 3:28:02 5_classification-with-multiple-outputs-optional 4_additional-neural-network-concepts\ 3:32:22 1_advanced-optimization 3:38:48 2_additional-layer-types 3_advice-for-applying-machine-learning\ 1_advice-for-applying-machine-learning\ 3:47:43 1_deciding-what-to-try-next 3:51:24 2_evaluating-a-model 4:01:50 3_model-selection-and-training-cross-validation-test-sets 2_bias-and-variance\ 4:16:42 1_diagnosing-bias-and-variance 4:27:55 2_regularization-and-bias-variance 4:38:31 3_establishing-a-baseline-level-of-performance 4:47:57 4_learning-curves 5:00:10 5_deciding-what-to-try-next-revisited 5:08:57 6_bias-variance-and-neural-networks 3_machine-learning-development-process\ 5:19:41 1_iterative-loop-of-ml-development 5:27:23 2_error-analysis 5:35:44 3_adding-data 5:50:07 4_transfer-learning-using-data-from-a-different-task 6:02:17 5_full-cycle-of-a-machine-learning-project 6:11:02 6_fairness-bias-and-ethics 4_skewed-datasets-optional\ 6:20:58 1_error-metrics-for-skewed-datasets 6:32:33 2_trading-off-precision-and-recall 4_decision-trees\ 1_decision-trees\ 6:44:22 1_decision-tree-model 6:51:27 2_learning-process 2_decision-tree-learning\ 7:02:47 1_measuring-purity 7:10:37 2_choosing-a-split-information-gain 7:22:29 3_putting-it-together 7:31:57 4_using-one-hot-encoding-of-categorical-features 7:37:22 5_continuous-valued-features 7:44:16 6_regression-trees-optional 3_tree-ensembles\ 7:54:07 1_using-multiple-decision-trees 7:58:03 2_sampling-with-replacement 8:02:02 3_random-forest-algorithm 8:08:25 4_xgboost 8:15:50 5_when-to-use-decision-trees