Guest
\ 0:00 Course Outline 5:21 Join Our Online Classroom! Learning and TensorFlow Fundamentals\ 9:22 What is deep learning 14:01 Why use deep learning 23:39 What are neural networks 34:06 What is deep learning already being used for 42:42 What is and why use TensorFlow 50:39 What is a Tensor 54:16 What we’re going to cover throughout the course 58:46 How to approach this course 1:04:20 Creating your first tensors with TensorFlow and () 1:23:05 Creating tensors with TensorFlow and () 1:30:13 Creating random tensors with TensorFlow 1:39:53 Shuffling the order of tensors 1:49:34 Creating tensors from NumPy arrays 2:01:29 Getting information from your tensors (tensor attributes) 2:13:26 Indexing and expanding tensors 2:26:00 Manipulating tensors with basic operations Matrix multiplication with tensors part 2:31:35 1 2:43:28 2 2:56:58 3 3:07:01 Changing the datatype of tensors 3:13:57 Tensor aggregation (finding the min, max, mean & more) 3:23:47 Tensor troubleshooting example (updating tensor datatypes) 3:30:00 Finding the positional minimum and maximum of a tensor (argmin and argmax) 3:39:32 Squeezing a tensor (removing all 1-dimension axes) 3:42:32 One-hot encoding tensors 3:48:18 Trying out more tensor math operations 3:53:06 Exploring TensorFlow and NumPy’s compatibility 3:58:49 Making sure our tensor operations run really fast on GPUs network regression with TensorFlow\ 4:09:09 Introduction to Neural Network Regression with TensorFlow 4:16:42 Inputs and outputs of a neural network regression model 4:25:41 Anatomy and architecture of a neural network regression model 4:33:37 Creating sample regression data (so we can Mdl it) 4:46:24 The major steps in modelling with TensorFlow Steps in improving a Mdl with TensorFlow part 5:06:39 1 5:12:42 2 5:22:08 3 Evaluating a TensorFlow Mdl part 5:34:41 1 (visualise, visualise, visualise) 5:42:06 2 (the three datasets) 5:53:07 3 (getting a Mdl summary) 6:10:26 4 (visualising a model’s layers) 6:17:41 5 (visualising a model’s predictions) 6:26:57 6 (common regression evaluation metrics) 6:35:03 Evaluating a TensorFlow regression Mdl part 7 (mean absolute error) 6:40:56 Evaluating a TensorFlow regression Mdl part 7 (mean square error) 6:44:15 Setting up TensorFlow modelling experiments part 1 (start with a simple model) 6:58:05 Setting up TensorFlow modelling experiments part 2 (increasing complexity) 7:09:35 Comparing and tracking your TensorFlow modelling experiments 7:19:55 How to save a TensorFlow model 7:28:15 How to load and use a saved TensorFlow model 7:38:31 (Optional) How to save and download files from Google Colab 7:44:50 Putting together what we’ve learned part 1 (preparing a dataset) 7:58:21 Putting together what we’ve learned part 2 (building a regression model) 8:11:42 Putting together what we’ve learned part 3 (improving our regression model) 8:27:29 Preprocessing data with feature scaling part 1 (what is feature scaling) 8:37:04 Preprocessing data with feature scaling part 2 (normalising our data) 8:48:01 Preprocessing data with feature scaling part 3 (fitting a Mdl on scaled data) network classification in TensorFlow\ 8:55:42 Introduction to neural network classification in TensorFlow 9:04:07 Example classification problems (and their inputs and outputs) 9:10:45 Input and output tensors of classification problems 9:17:07 Typical architecture of neural network classification models with TensorFlow 9:26:43 Creating and viewing classification data to model 9:38:18 Checking the input and output shapes of our classification data 9:42:56 Building a not very good classification Mdl with TensorFlow 9:55:07 Trying to improve our not very good classification model 10:04:20 Creating a function to view our model’s not so good predictions 10:19:29 Make our poor classification Mdl work for a regression dataset 10:31:48 Non-linearity part 1 Straight lines and non-straight lines 10:41:27 Non-linearity part 2 Building our first neural network with non-linearity 10:47:14 Non-linearity part 3 Upgrading our non-linear Mdl with more layers 10:57:33 Non-linearity part 4 Modelling our non-linear data once and for all 11:06:11 Non-linearity part 5 Replicating non-linear activation functions from scratch 11:20:38 Getting great results in less time by tweaking the learning rate 11:35:26 Using the TensorFlow History object to plot a model’s loss curves 11:41:38 Using callbacks to find a model’s ideal learning rate 11:59:10 Training and evaluating a Mdl with an ideal learning rate
