Guest
Series fundamentals in TensorFlow Milestone Project 3 BitPredict\ 3:16 Writing a preprocessing function to turn time series data into windows & labels 26:51 Turning our windowed time series data into training and test sets 36:53 Creating a modelling checkpoint callback to save our best performing model 44:18 Mdl 1 Building, compiling and fitting a deep learning Mdl on Bitcoin data 1:01:16 Creating a function to make predictions with our trained models 1:15:20 Mdl 2 Building, fitting and evaluating a deep Mdl with a larger window size 1:33:03 Mdl 3 Building, fitting and evaluating a Mdl with a larger horizon size 1:46:19 Adjusting the evaluation function to work for predictions with larger horizons 1:54:53 Mdl 3 Visualizing the results 2:03:37 Comparing our modelling experiments so far and discussing autocorrelation 2:13:21 Preparing data for building a Conv1D model 2:26:43 Mdl 4 Building, fitting and evaluating a Conv1D Mdl on our Bitcoin data 2:41:35 Mdl 5 Building, fitting and evaluating a LSTM (RNN) Mdl on our Bitcoin data 2:57:40 Investigating how to turn our univariate time series into multivariate 3:11:33 Creating and plotting a multivariate time series with BTC price and block reward 3:23:45 Preparing our multivariate time series for a model 3:37:23 Mdl 6 Building, fitting and evaluating a multivariate time series model 3:46:48 Mdl 7 Discussing what we’re going to be doing with the N-BEATS algorithm 3:56:27 Mdl 7 Replicating the N-BEATS basic block with TensorFlow layer subclassing 4:15:06 Mdl 7 Testing our N-BEATS block implementation with dummy data inputs 4:30:08 Mdl 7 Creating a performant data pipeline for the N-BEATS Mdl with 4:44:18 Mdl 7 Setting up hyperparameters for the N-BEATS algorithm 4:53:09 Mdl 7 Getting ready for residual connections 5:06:05 Mdl 7 Outlining the steps we’re going to take to build the N-BEATS model 5:16:11 Mdl 7 Putting together the pieces of the puzzle of the N-BEATS model 5:38:33 Mdl 7 Plotting the N-BEATS algorithm we’ve created and admiring its beauty 5:45:20 Mdl 8 Ensemble Mdl overview 5:50:03 Mdl 8 Building, compiling and fitting an ensemble of models 6:10:08 Mdl 8 Making and evaluating predictions with our ensemble model 6:26:17 Discussing the importance of prediction intervals in forecasting 6:39:13 Getting the upper and lower bounds of our prediction intervals 6:47:11 Plotting the prediction intervals of our ensemble Mdl predictions 7:00:13 (Optional) Discussing the types of uncertainty in machine learning 7:13:55 Mdl 9 Preparing data to create a Mdl capable of predicting into the future 7:22:19 Mdl 9 Building, compiling and fitting a future predictions model 7:27:21 Mdl 9 Discussing what’s required for our Mdl to make future predictions 7:35:51 Mdl 9 Creating a function to make forecasts into the future 7:48:00 Mdl 9 Plotting our model’s future forecasts 8:01:09 Mdl 10 Introducing the turkey problem and making data for it 8:15:24 Mdl 10 Building a Mdl to predict on turkey data (why forecasting is BS) 8:29:03 Comparing the results of all of our models and discussing where to go next the TensorFlow Developer Certificate Exam\ 8:42:02 What is the TensorFlow Developer Certification 8:47:31 Why the TensorFlow Developer Certification 8:54:28 How to prepare (your brain) for the TensorFlow Developer Certification 9:02:43 How to prepare (your computer) for the TensorFlow Developer Certification 9:15:27 What to do after the TensorFlow Developer Certification exam Machine Learning Primer\ 9:17:40 What is Machine Learning 9:24:33 AIMachine LearningData Science 9:29:24 Exercise Machine Learning Playground 9:35:40 How Did We Get Here 9:41:44 Exercise YouTube Recommendation Engine 9:46:09 Types of Machine Learning 9:50:50 What Is Machine Learning Round 2 9:55:35 Section Review Machine Learning and Data Science Framework\ 9:57:24 Section Overview 10:00:32 Introducing Our Framework 10:03:11 6 Step Machine Learning Framework 10:08:10 Types of Machine Learning Problems 10:18:42 Types of Data 10:23:33 Types of Evaluation 10:27:04 Features In Data 10:32:27 Modelling - Splitting Data 10:38:25 Modelling - Picking the Model 10:43:01 Modelling - Tuning 10:46:18 Modelling - Comparison 10:55:51 Experimentation 10:59:26 Tools We Will Use Pandas for Data Analysis\ 11:03:26 Section Overview 11:05:54 Pandas Introduction 11:10:23 Series, Data Frames and CSVs 11:23:45 Describing Data with Pandas 11:33:34 Selecting and Viewing Data with Pandas 11:44:42 Selecting and Viewing Data with Pandas Part 2 11:57:49 Manipulating Data
