Section 1 : Introduction to GCP
|
Lecture 1 | Introduction to Google Cloud Platform | 00:02:14 Duration |
|
Lecture 2 | GCP vs AWS vs Azure - Why choose GCP | 00:06:04 Duration |
|
Lecture 3 | AI & ML services in Google Cloud | 00:08:55 Duration |
Section 2 : BigQuery ML (BQML) introduction
|
Lecture 1 | What is BigQuery ML | 00:04:38 Duration |
|
Lecture 2 | Conventional ML challenges and How Big query is addressing them | 00:07:37 Duration |
|
Lecture 3 | BigQuery ML Features | 00:06:36 Duration |
|
Lecture 4 | Advantages of BigQuery ML | 00:04:02 Duration |
|
Lecture 5 | LifecycleWorkflow of a BigQuery ML Project | 00:04:56 Duration |
|
Lecture 6 | BQML supported models | 00:05:47 Duration |
Section 3 : BigQuery Basics - Crash course
|
Lecture 1 | Announcement | 00:01:26 Duration |
|
Lecture 2 | Setup a GCP account | |
|
Lecture 3 | Important Note | |
|
Lecture 4 | Create a Project | 00:04:25 Duration |
|
Lecture 5 | BigQuery UI Tour | 00:04:02 Duration |
|
Lecture 6 | Create a Dataset | 00:04:29 Duration |
|
Lecture 7 | Create a Table | 00:08:01 Duration |
Section 4 : Linear Regression
Section 5 : Hyperparameter Tuning in BigQuery
|
Lecture 1 | What is Hyperparameter Tuning | 00:02:39 Duration |
|
Lecture 2 | Hyperparameter Tuning Options in BigQuery | 00:08:31 Duration |
|
Lecture 3 | Tune the Linear regression model | 00:06:01 Duration |
|
Lecture 4 | ML |
Section 6 : Model Explainability Functions
|
Lecture 1 | Why Model Explainability is important | 00:03:40 Duration |
|
Lecture 2 | Model Explainability Functions in BigQuery | |
|
Lecture 3 | ML | |
|
Lecture 4 | List of functions supported by all models |
Section 7 : Logistic regression
|
Lecture 1 | What is Logistic regression | 00:03:09 Duration |
|
Lecture 2 | Sigmoid Function | 00:03:42 Duration |
|
Lecture 3 | Logistic regression Example Use case | 00:04:44 Duration |
|
Lecture 4 | Model Training - Write Create model Query for Logistic regression | 00:03:04 Duration |
|
Lecture 5 | Evaluation metrics Fundamentals explained | 00:06:55 Duration |
|
Lecture 6 | Precision, Recall, Accuracy, F1 score | 00:07:38 Duration |
|
Lecture 7 | Evaluation Functions in BigQuery | 00:05:15 Duration |
|
Lecture 8 | Prediction Function (ML | 00:04:12 Duration |
|
Lecture 9 | Applications of Logistic regression | 00:02:16 Duration |
Section 8 : Feature Pre-processing
|
Lecture 1 | Automatic Feature Pre-processing | 00:09:32 Duration |
|
Lecture 2 | Manual Feature Pre-processing - Part 1 | 00:10:25 Duration |
|
Lecture 3 | Manual Feature Pre-processing - Part 2 | 00:03:07 Duration |
|
Lecture 4 | FEATURE_INFO Function |
Section 9 : K-means Clustering
|
Lecture 1 | What is Clustering | 00:04:00 Duration |
|
Lecture 2 | K-means algorithm working | 00:04:10 Duration |
|
Lecture 3 | Advantages & Disadvantages of K-means | 00:03:27 Duration |
|
Lecture 4 | Applications of K-means algorithm | 00:03:01 Duration |
|
Lecture 5 | Options in Create model query | 00:06:43 Duration |
|
Lecture 6 | K-means Example in BigQuery - Create model | 00:07:54 Duration |
|
Lecture 7 | K-means Example in BigQuery - Evaluation | 00:06:03 Duration |
|
Lecture 8 | K-means Example in BigQuery - Prediction | 00:04:09 Duration |
|
Lecture 9 | K-means Example in BigQuery - Anomaly detection | 00:05:43 Duration |
Section 10 : Boosted Trees
|
Lecture 1 | What is Boosting and Why it is needed | |
|
Lecture 2 | Boosted Tree working explained | 00:04:40 Duration |
|
Lecture 3 | Types of Boosting | 00:05:22 Duration |
|
Lecture 4 | Options in Create model query - Part 1 | 00:08:15 Duration |
|
Lecture 5 | Options in Create model query - Part 2 | 00:08:50 Duration |
|
Lecture 6 | Boosted Tree Example - Use Case Intro & EDA | 00:05:55 Duration |
|
Lecture 7 | Boosted Tree Example - Feature Engineering Part 1 | 00:02:33 Duration |
|
Lecture 8 | Boosted Tree Example - Feature Engineering Part 2 | 00:10:49 Duration |
|
Lecture 9 | Boosted Tree Example - Create model | |
|
Lecture 10 | Boosted Tree Example - Hyperparameter Tuning | 00:05:28 Duration |
|
Lecture 11 | Boosted Tree Example - Evaluation | 00:04:39 Duration |
Section 11 : Model management Operations in BigQuery
|
Lecture 1 | Introduction | 00:02:31 Duration |
|
Lecture 2 | Operations on Models - Part 1 | 00:05:31 Duration |
|
Lecture 3 | Operations on Models - Part 2 | 00:07:52 Duration |
Section 12 : Deep Neural Network (DNN)
|
Lecture 1 | What is Artificial Neural Network | 00:05:41 Duration |
|
Lecture 2 | Working of Artificial Neural Network | 00:08:10 Duration |
|
Lecture 3 | DNN working explained | 00:07:15 Duration |
|
Lecture 4 | Activation Functions - Sigmoid, TanH | 00:08:01 Duration |
|
Lecture 5 | Activation Functions - RELU | 00:05:31 Duration |
|
Lecture 6 | Which Activation Function to choose | 00:03:11 Duration |
|
Lecture 7 | Dropout technique to avoid Overfitting | 00:05:08 Duration |
|
Lecture 8 | HIDDEN_UNITS Option | 00:05:08 Duration |
|
Lecture 9 | Optimizer in DNN | 00:04:25 Duration |
|
Lecture 10 | Other Options in DNN | |
|
Lecture 11 | DNN Example Use Case | 00:05:34 Duration |
|
Lecture 12 | DNN Example Implementation in BigQuery ML | 00:07:12 Duration |
Section 13 : BigQuery ML Pricing
|
Lecture 1 | Free operations in BigQuery ML | 00:02:15 Duration |
|
Lecture 2 | What is Flat rate pricing model | 00:04:45 Duration |
|
Lecture 3 | Costs involved in Flat rate pricing model | 00:06:00 Duration |
|
Lecture 4 | Reservations | 00:05:50 Duration |
|
Lecture 5 | BigQuery ML On-demand pricing model | 00:04:46 Duration |
|
Lecture 6 | Calculate price for Create Model query | 00:03:39 Duration |
Section 14 : ARIMA+ for Time series Forecasting
|
Lecture 1 | What is Time series Forecasting | |
|
Lecture 2 | Components of Time series | 00:03:07 Duration |
|
Lecture 3 | Stationarity in Time series | 00:03:22 Duration |
|
Lecture 4 | Auto regression (AR) in ARIMA | 00:07:34 Duration |
|
Lecture 5 | Moving Average (MA) in ARIMA | 00:07:14 Duration |
|
Lecture 6 | ARIMA+ Options - Part 1 | 00:06:35 Duration |
|
Lecture 7 | ARIMA+ Options - Part 2 | 00:03:40 Duration |
|
Lecture 8 | ARIMA+ Example - Use case & EDA | 00:06:17 Duration |
|
Lecture 9 | ARIMA+ Example - Create Model | 00:07:57 Duration |
|
Lecture 10 | ARIMA+ Example - Evaluation | 00:10:12 Duration |
|
Lecture 11 | ARIMA+ Example - Inferencing Functions | 00:06:25 Duration |
|
Lecture 12 | ARIMA+ Example - Model Explainability | 00:05:26 Duration |
Section 15 : Additional Learnings
|
Lecture 1 | Google Cloud SDK setup | 00:01:47 Duration |