Section 1 : Introduction
Lecture 1 INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 2 About Certification
Lecture 3 About Proctor Testing
Lecture 4 All Course Resources + Notebooks
Lecture 5 Remove - INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM

Section 2 : Deep Learning and TensorFlow Fundamentals
Lecture 1 What is deep learning 00:04:23 Duration
Lecture 2 Why use deep learning 00:09:39 Duration
Lecture 3 What are neural networks 00:10:26 Duration
Lecture 4 What is deep learning already being used for 00:08:37 Duration
Lecture 5 What is and why use TensorFlow 00:07:56 Duration
Lecture 6 What is a Tensor 00:03:38 Duration
Lecture 7 What we're going to cover throughout the course 00:04:29 Duration
Lecture 8 How to approach this course 00:05:34 Duration
Lecture 9 Need A Refresher
Lecture 10 Creating your first tensors with TensorFlow and tf 00:18:45 Duration
Lecture 11 Creating tensors with TensorFlow and tf 00:07:07 Duration
Lecture 12 Creating random tensors with TensorFlow 00:09:40 Duration
Lecture 13 Shuffling the order of tensors 00:09:40 Duration
Lecture 14 Creating tensors from NumPy arrays 00:11:55 Duration
Lecture 15 Getting information from your tensors (tensor attributes) 00:11:57 Duration
Lecture 16 Indexing and expanding tensors 00:12:33 Duration
Lecture 17 Manipulating tensors with basic operations 00:05:34 Duration
Lecture 18 Matrix multiplication with tensors part 1 00:11:53 Duration
Lecture 19 Matrix multiplication with tensors part 2 00:13:29 Duration
Lecture 20 Matrix multiplication with tensors part 3 00:10:03 Duration
Lecture 21 Changing the datatype of tensors 00:06:56 Duration
Lecture 22 Tensor aggregation (finding the min, max, mean & more) 00:09:49 Duration
Lecture 23 Tensor troubleshooting example (updating tensor datatypes) 00:06:14 Duration
Lecture 24 Finding the positional minimum and maximum of a tensor (argmin and argmax) 00:09:31 Duration
Lecture 25 Squeezing a tensor (removing all 1-dimension axes) 00:03:00 Duration
Lecture 26 One-hot encoding tensors 00:05:46 Duration
Lecture 27 Trying out more tensor math operations 00:04:48 Duration
Lecture 28 Exploring TensorFlow and NumPy's compatibility 00:05:43 Duration
Lecture 29 Making sure our tensor operations run really fast on GPUs 00:10:19 Duration
Lecture 30 TensorFlow Fundamentals challenge, exercises & extra-curriculum
Lecture 31 INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 32 About Certification

Section 3 : Neural network regression with TensorFlow
Lecture 1 Introduction to Neural Network Regression with TensorFlow 00:07:33 Duration
Lecture 2 Inputs and outputs of a neural network regression model 00:08:59 Duration
Lecture 3 Anatomy and architecture of a neural network regression model 00:07:55 Duration
Lecture 4 Creating sample regression data (so we can model it) 00:12:47 Duration
Lecture 5 Note Code update for upcoming lecture(s) for TensorFlow 2
Lecture 6 The major steps in modelling with TensorFlow 00:20:15 Duration
Lecture 7 Steps in improving a model with TensorFlow part 1 00:06:03 Duration
Lecture 8 Steps in improving a model with TensorFlow part 2 00:09:26 Duration
Lecture 9 Steps in improving a model with TensorFlow part 3 00:12:33 Duration
Lecture 10 Evaluating a TensorFlow model part 1 (visualise, visualise, visualise) 00:07:24 Duration
Lecture 11 Evaluating a TensorFlow model part 2 (the three datasets) 00:11:02 Duration
Lecture 12 Evaluating a TensorFlow model part 3 (getting a model summary) 00:17:18 Duration
Lecture 13 Evaluating a TensorFlow model part 4 (visualising a model's layers) 00:07:15 Duration
Lecture 14 Evaluating a TensorFlow model part 5 (visualising a model's predictions) 00:09:16 Duration
Lecture 15 Evaluating a TensorFlow model part 6 (common regression evaluation metrics) 00:08:06 Duration
Lecture 16 Evaluating a TensorFlow regression model part 7 (mean absolute error) 00:05:53 Duration
Lecture 17 Evaluating a TensorFlow regression model part 7 (mean square error) 00:03:19 Duration
Lecture 18 Setting up TensorFlow modelling experiments part 1 (start with a simple model) 00:13:50 Duration
Lecture 19 Setting up TensorFlow modelling experiments part 2 (increasing complexity) 00:11:30 Duration
Lecture 20 Comparing and tracking your TensorFlow modelling experiments 00:10:20 Duration
Lecture 21 How to save a TensorFlow model 00:08:20 Duration
Lecture 22 How to load and use a saved TensorFlow model 00:10:16 Duration
Lecture 23 (Optional) How to save and download files from Google Colab 00:06:19 Duration
Lecture 24 Putting together what we've learned part 1 (preparing a dataset) 00:13:31 Duration
Lecture 25 Putting together what we've learned part 2 (building a regression model) 00:13:21 Duration
Lecture 26 Putting together what we've learned part 3 (improving our regression model) 00:15:47 Duration
Lecture 27 Preprocessing data with feature scaling part 1 (what is feature scaling) 00:09:34 Duration
Lecture 28 Preprocessing data with feature scaling part 2 (normalising our data) 00:10:57 Duration
Lecture 29 Preprocessing data with feature scaling part 3 (fitting a model on scaled data) 00:07:41 Duration
Lecture 30 TensorFlow Regression challenge, exercises & extra-curriculum
Lecture 31 Learning Guideline

Section 4 : Neural network classification in TensorFlow
Lecture 1 Introduction to neural network classification in TensorFlow 00:08:25 Duration
Lecture 2 Example classification problems (and their inputs and outputs) 00:06:38 Duration
Lecture 3 Input and output tensors of classification problems 00:06:22 Duration
Lecture 4 Typical architecture of neural network classification models with TensorFlow 00:09:36 Duration
Lecture 5 Creating and viewing classification data to model 00:11:34 Duration
Lecture 6 Checking the input and output shapes of our classification data 00:04:38 Duration
Lecture 7 Building a not very good classification model with TensorFlow 00:12:11 Duration
Lecture 8 Trying to improve our not very good classification model 00:09:13 Duration
Lecture 9 Creating a function to view our model's not so good predictions 00:15:08 Duration
Lecture 10 Note Updates for TensorFlow 2
Lecture 11 Make our poor classification model work for a regression dataset 00:12:19 Duration
Lecture 12 Non-linearity part 1 Straight lines and non-straight lines 00:09:39 Duration
Lecture 13 Non-linearity part 2 Building our first neural network with non-linearity 00:05:47 Duration
Lecture 14 Non-linearity part 3 Upgrading our non-linear model with more layers 00:10:19 Duration
Lecture 15 Non-linearity part 4 Modelling our non-linear data once and for all 00:08:38 Duration
Lecture 16 Non-linearity part 5 Replicating non-linear activation functions from scratch
Lecture 17 Getting great results in less time by tweaking the learning rate 00:14:47 Duration
Lecture 18 Using the TensorFlow History object to plot a model's loss curves 00:06:12 Duration
Lecture 19 Using callbacks to find a model's ideal learning rate 00:17:32 Duration
Lecture 20 Training and evaluating a model with an ideal learning rate 00:09:21 Duration
Lecture 21 Introducing more classification evaluation methods 00:06:05 Duration
Lecture 22 Finding the accuracy of our classification model 00:04:18 Duration
Lecture 23 Creating our first confusion matrix (to see where our model is getting confused) 00:08:28 Duration
Lecture 24 Making our confusion matrix prettier 00:14:01 Duration
Lecture 25 Putting things together with multi-class classification part 1 Getting the data 00:10:37 Duration
Lecture 26 Multi-class classification part 2 Becoming one with the data 00:07:08 Duration
Lecture 27 Multi-class classification part 3 Building a multi-class classification model 00:15:38 Duration
Lecture 28 Multi-class classification part 4 Improving performance with normalisation 00:12:43 Duration
Lecture 29 Multi-class classification part 5 Comparing normalised and non-normalised data 00:04:14 Duration
Lecture 30 Multi-class classification part 6 Finding the ideal learning rate 00:10:39 Duration
Lecture 31 Multi-class classification part 7 Evaluating our model 00:13:16 Duration
Lecture 32 Multi-class classification part 8 Creating a confusion matrix 00:04:26 Duration
Lecture 33 Multi-class classification part 9 Visualising random model predictions
Lecture 34 What patterns is our model learning 00:15:33 Duration
Lecture 35 TensorFlow classification challenge, exercises & extra-curriculum

Section 5 : Computer Vision and Convolutional Neural Networks in TensorFlow
Lecture 1 Introduction to Computer Vision with TensorFlow 00:09:36 Duration
Lecture 2 Introduction to Convolutional Neural Networks (CNNs) with TensorFlow 00:08:00 Duration
Lecture 3 Downloading an image dataset for our first Food Vision model 00:08:27 Duration
Lecture 4 Becoming One With Data 00:05:05 Duration
Lecture 5 Becoming One With Data Part 2 00:12:26 Duration
Lecture 6 Becoming One With Data Part 3 00:04:23 Duration
Lecture 7 Building an end to end CNN Model 00:18:18 Duration
Lecture 8 Using a GPU to run our CNN model 5x faster 00:09:17 Duration
Lecture 9 Trying a non-CNN model on our image data 00:08:51 Duration
Lecture 10 Improving our non-CNN model by adding more layers 00:09:52 Duration
Lecture 11 Breaking our CNN model down part 1 Becoming one with the data 00:09:03 Duration
Lecture 12 Breaking our CNN model down part 2 Preparing to load our data 00:11:46 Duration
Lecture 13 INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 14 Breaking our CNN model down part 4 Building a baseline CNN model 00:08:03 Duration
Lecture 15 Breaking our CNN model down part 5 Looking inside a Conv2D layer 00:15:21 Duration
Lecture 16 About Certification
Lecture 17 Breaking our CNN model down part 7 Evaluating our CNN's training curves 00:11:46 Duration
Lecture 18 About Proctor Testing
Lecture 19 Remove - INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 20 Breaking our CNN model down part 10 Visualizing our augmented data 00:15:04 Duration
Lecture 21 INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 22 About Certification
Lecture 23 About Proctor Testing
Lecture 24 Downloading a custom image to make predictions on 00:04:54 Duration
Lecture 25 Writing a helper function to load and preprocessing custom images 00:10:01 Duration
Lecture 26 Making a prediction on a custom image with our trained CNN 00:10:09 Duration
Lecture 27 Multi-class CNN's part 1 Becoming one with the data 00:14:59 Duration
Lecture 28 Multi-class CNN's part 2 Preparing our data (turning it into tensors) 00:06:38 Duration
Lecture 29 Multi-class CNN's part 3 Building a multi-class CNN model 00:07:25 Duration
Lecture 30 Multi-class CNN's part 4 Fitting a multi-class CNN model to the data 00:06:03 Duration
Lecture 31 Multi-class CNN's part 5 Evaluating our multi-class CNN model 00:04:51 Duration
Lecture 32 Multi-class CNN's part 6 Trying to fix overfitting by removing layers 00:12:20 Duration
Lecture 33 Remove - INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM
Lecture 34 Multi-class CNN's part 8 Things you could do to improve your CNN model 00:04:24 Duration
Lecture 35 About Certification
Lecture 36 Saving and loading our trained CNN model 00:06:21 Duration
Lecture 37 TensorFlow computer vision and CNNs challenge, exercises & extra-curriculum

Section 6 : Transfer Learning in TensorFlow Part 1 Feature extraction
Lecture 1 What is and why use transfer learning 00:10:12 Duration
Lecture 2 Downloading and preparing data for our first transfer learning model 00:14:40 Duration
Lecture 3 Introducing Callbacks in TensorFlow and making a callback to track our models 00:10:01 Duration
Lecture 4 Exploring the TensorFlow Hub website for pretrained models 00:09:51 Duration
Lecture 5 Building and compiling a TensorFlow Hub feature extraction model
Lecture 6 Blowing our previous models out of the water with transfer learning 00:09:13 Duration
Lecture 7 Plotting the loss curves of our ResNet feature extraction model 00:07:36 Duration
Lecture 8 Building and training a pre-trained EfficientNet model on our data 00:09:42 Duration
Lecture 9 Different Types of Transfer Learning 00:11:40 Duration
Lecture 10 Comparing Our Model's Results 00:15:17 Duration
Lecture 11 TensorFlow Transfer Learning Part 1 challenge, exercises & extra-curriculum
Lecture 12 Exercise Imposter Syndrome 00:02:56 Duration

Section 7 : Transfer Learning in TensorFlow Part 2 Fine tuning
Lecture 1 Introduction to Transfer Learning in TensorFlow Part 2 Fine-tuning 00:06:16 Duration
Lecture 2 Importing a script full of helper functions (and saving lots of space) 00:07:35 Duration
Lecture 3 Downloading and turning our images into a TensorFlow BatchDataset 00:15:39 Duration
Lecture 4 Discussing the four (actually five) modelling experiments we're running 00:02:15 Duration
Lecture 5 Comparing the TensorFlow Keras Sequential API versus the Functional API 00:02:34 Duration
Lecture 6 Creating our first model with the TensorFlow Keras Functional API 00:11:39 Duration
Lecture 7 Compiling and fitting our first Functional API model 00:10:54 Duration
Lecture 8 Getting a feature vector from our trained model 00:13:39 Duration
Lecture 9 Drilling into the concept of a feature vector 00:03:43 Duration
Lecture 10 Downloading and preparing the data for Model 1 (1 percent of training data) 00:09:52 Duration
Lecture 11 Building a data augmentation layer to use inside our model 00:12:06 Duration
Lecture 12 Note Small fix for next video, for images not augmenting
Lecture 13 Visualizing what happens when images pass through our data augmentation layer 00:10:56 Duration
Lecture 14 Building Model 1 (with a data augmentation layer and 1% of training data) 00:15:55 Duration
Lecture 15 Building Model 2 (with a data augmentation layer and 10% of training data) 00:16:37 Duration
Lecture 16 Creating a ModelCheckpoint to save our model's weights during training 00:07:25 Duration
Lecture 17 Fitting and evaluating Model 2 (and saving its weights using ModelCheckpoint) 00:07:14 Duration
Lecture 18 Loading and comparing saved weights to our existing trained Model 2 00:07:18 Duration
Lecture 19 Preparing Model 3 (our first fine-tuned model) 00:20:27 Duration
Lecture 20 Fitting and evaluating Model 3 (our first fine-tuned model) 00:07:46 Duration
Lecture 21 Comparing our model's results before and after fine-tuning 00:10:27 Duration
Lecture 22 Downloading and preparing data for our biggest experiment yet (Model 4) 00:06:25 Duration
Lecture 23 Preparing our final modelling experiment (Model 4) 00:12:00 Duration
Lecture 24 Fine-tuning Model 4 on 100% of the training data and evaluating its results 00:10:19 Duration
Lecture 25 Comparing our modelling experiment results in TensorBoard 00:10:46 Duration
Lecture 26 How to view and delete previous TensorBoard experiments 00:02:04 Duration
Lecture 27 Transfer Learning in TensorFlow Part 2 challenge, exercises and extra-curriculum

Section 8 : Transfer Learning with TensorFlow Part 3 Scaling Up
Lecture 1 Introduction to Transfer Learning Part 3 Scaling Up 00:06:20 Duration
Lecture 2 Getting helper functions ready and downloading data to model 00:13:34 Duration
Lecture 3 Outlining the model we're going to build and building a ModelCheckpoint callback 00:05:39 Duration
Lecture 4 Creating a data augmentation layer to use with our model 00:04:40 Duration
Lecture 5 Creating a headless EfficientNetB0 model with data augmentation built in 00:08:59 Duration
Lecture 6 Fitting and evaluating our biggest transfer learning model yet 00:07:57 Duration
Lecture 7 Unfreezing some layers in our base model to prepare for fine-tuning 00:11:28 Duration
Lecture 8 Fine-tuning our feature extraction model and evaluating its performance 00:08:24 Duration
Lecture 9 Saving and loading our trained model 00:06:26 Duration
Lecture 10 Downloading a pretrained model to make and evaluate predictions with 00:06:34 Duration
Lecture 11 Making predictions with our trained model on 25,250 test samples 00:12:47 Duration
Lecture 12 Unravelling our test dataset for comparing ground truth labels to predictions 00:06:05 Duration
Lecture 13 Confirming our model's predictions are in the same order as the test labels 00:05:17 Duration
Lecture 14 Creating a confusion matrix for our model's 101 different classes 00:12:08 Duration
Lecture 15 Evaluating every individual class in our dataset 00:14:16 Duration
Lecture 16 Plotting our model's F1-scores for each separate class 00:07:36 Duration
Lecture 17 Creating a function to load and prepare images for making predictions 00:12:09 Duration
Lecture 18 Making predictions on our test images and evaluating them 00:16:06 Duration
Lecture 19 Discussing the benefits of finding your model's most wrong predictions 00:06:09 Duration
Lecture 20 Writing code to uncover our model's most wrong predictions 00:11:16 Duration
Lecture 21 Plotting and visualising the samples our model got most wrong 00:10:36 Duration
Lecture 22 Making predictions on and plotting our own custom images 00:09:50 Duration
Lecture 23 Transfer Learning in TensorFlow Part 3 challenge, exercises and extra-curriculum

Section 9 : Milestone Project 1 Food Vision Big™
Lecture 1 Introduction to Milestone Project 1 Food Vision Big™ 00:05:44 Duration
Lecture 2 Making sure we have access to the right GPU for mixed precision training 00:10:18 Duration
Lecture 3 Getting helper functions ready 00:03:06 Duration
Lecture 4 Introduction to TensorFlow Datasets (TFDS) 00:12:03 Duration
Lecture 5 Exploring and becoming one with the data (Food101 from TensorFlow Datasets) 00:15:56 Duration
Lecture 6 Creating a preprocessing function to prepare our data for modelling 00:15:50 Duration
Lecture 7 Batching and preparing our datasets (to make them run fast) 00:13:48 Duration
Lecture 8 Exploring what happens when we batch and prefetch our data 00:06:49 Duration
Lecture 9 Creating modelling callbacks for our feature extraction model 00:07:14 Duration
Lecture 10 Note Mixed Precision producing errors for TensorFlow 2
Lecture 11 Turning on mixed precision training with TensorFlow 00:10:05 Duration
Lecture 12 Creating a feature extraction model capable of using mixed precision training 00:12:42 Duration
Lecture 13 Checking to see if our model is using mixed precision training layer by layer 00:07:57 Duration
Lecture 14 Training and evaluating a feature extraction model (Food Vision Big™) 00:10:19 Duration
Lecture 15 Introducing your Milestone Project 1 challenge build a model to beat DeepFood 00:07:48 Duration
Lecture 16 Milestone Project 1 Food Vision Big™, exercises and extra-curriculum

Section 10 : NLP Fundamentals in TensorFlow
Lecture 1 Welcome to natural language processing with TensorFlow!
Lecture 2 Introduction to Natural Language Processing 00:12:52 Duration
Lecture 3 Example NLP inputs and outputs 00:07:22 Duration
Lecture 4 The typical architecture of a Recurrent Neural Network (RNN) 00:09:03 Duration
Lecture 5 Preparing a notebook for our first NLP with TensorFlow project 00:08:53 Duration
Lecture 6 Becoming one with the data and visualising a text dataset 00:16:41 Duration
Lecture 7 Splitting data into training and validation sets 00:06:27 Duration
Lecture 8 Converting text data to numbers using tokenisation and embeddings (overview) 00:09:23 Duration
Lecture 9 Setting up a TensorFlow TextVectorization layer to convert text to numbers 00:17:10 Duration
Lecture 10 Mapping the TextVectorization layer to text data and turning it into numbers 00:11:03 Duration
Lecture 11 Creating an Embedding layer to turn tokenised text into embedding vectors 00:12:27 Duration
Lecture 12 Discussing the various modelling experiments we're going to run 00:08:58 Duration
Lecture 13 Model 0 Building a baseline model to try and improve upon 00:09:25 Duration
Lecture 14 Creating a function to track and evaluate our model's results 00:12:14 Duration
Lecture 15 Model 1 Building, fitting and evaluating our first deep model on text data 00:20:52 Duration
Lecture 16 Visualising our model's learned word embeddings with TensorFlow's projector tool 00:20:44 Duration
Lecture 17 High-level overview of Recurrent Neural Networks (RNNs) + where to learn more 00:09:34 Duration
Lecture 18 Model 2 Building, fitting and evaluating our first TensorFlow RNN model (LSTM) 00:18:17 Duration
Lecture 19 Model 3 Building, fitting and evaluating a GRU-cell powered RNN 00:16:56 Duration
Lecture 20 Model 4 Building, fitting and evaluating a bidirectional RNN model 00:19:35 Duration
Lecture 21 Discussing the intuition behind Conv1D neural networks for text and sequences 00:19:32 Duration
Lecture 22 Model 5 Building, fitting and evaluating a 1D CNN for text 00:09:58 Duration
Lecture 23 Using TensorFlow Hub for pretrained word embeddings (transfer learning for NLP) 00:13:45 Duration
Lecture 24 Model 6 Building, training and evaluating a transfer learning model for NLP 00:10:46 Duration
Lecture 25 Preparing subsets of data for model 7 (same as model 6 but 10% of data) 00:10:52 Duration
Lecture 26 Model 7 Building, training and evaluating a transfer learning model on 10% data 00:10:04 Duration
Lecture 27 Fixing our data leakage issue with model 7 and retraining it 00:13:43 Duration
Lecture 28 Comparing all our modelling experiments evaluation metrics 00:13:14 Duration
Lecture 29 Uploading our model's training logs to TensorBoard and comparing them 00:11:15 Duration
Lecture 30 Saving and loading in a trained NLP model with TensorFlow 00:10:25 Duration
Lecture 31 Downloading a pretrained model and preparing data to investigate predictions 00:13:25 Duration
Lecture 32 Visualising our model's most wrong predictions 00:08:29 Duration
Lecture 33 Making and visualising predictions on the test dataset 00:08:27 Duration
Lecture 34 Understanding the concept of the speedscore tradeoff 00:15:02 Duration
Lecture 35 NLP Fundamentals in TensorFlow challenge, exercises and extra-curriculum

Section 11 : Milestone Project 2 SkimLit
Lecture 1 Introduction to Milestone Project 2 SkimLit 00:14:20 Duration
Lecture 2 What we're going to cover in Milestone Project 2 (NLP for medical abstracts) 00:07:22 Duration
Lecture 3 SkimLit inputs and outputs 00:11:02 Duration
Lecture 4 Setting up our notebook for Milestone Project 2 (getting the data) 00:14:58 Duration
Lecture 5 Visualising examples from the dataset (becoming one with the data) 00:13:18 Duration
Lecture 6 Writing a preprocessing function to structure our data for modelling
Lecture 7 Performing visual data analysis on our preprocessed text 00:07:55 Duration
Lecture 8 Turning our target labels into numbers (ML models require numbers) 00:13:15 Duration
Lecture 9 Model 0 Creating, fitting and evaluating a baseline model for SkimLit 00:09:26 Duration
Lecture 10 Preparing our data for deep sequence models 00:09:56 Duration
Lecture 11 Creating a text vectoriser to map our tokens (text) to numbers 00:14:07 Duration
Lecture 12 Creating a custom token embedding layer with TensorFlow 00:09:14 Duration
Lecture 13 Creating fast loading dataset with the TensorFlow tf 00:09:50 Duration
Lecture 14 Model 1 Building, fitting and evaluating a Conv1D with token embeddings 00:17:21 Duration
Lecture 15 Preparing a pretrained embedding layer from TensorFlow Hub for Model 2 00:10:53 Duration
Lecture 16 Model 2 Building, fitting and evaluating a Conv1D model with token embeddings 00:11:31 Duration
Lecture 17 Creating a character-level tokeniser with TensorFlow's TextVectorization layer 00:23:24 Duration
Lecture 18 Creating a character-level embedding layer with tf 00:07:44 Duration
Lecture 19 Model 3 Building, fitting and evaluating a Conv1D model on character embeddings 00:13:45 Duration
Lecture 20 Discussing how we're going to build Model 4 (character + token embeddings) 00:06:05 Duration
Lecture 21 Model 4 Building a multi-input model (hybrid token + character embeddings) 00:15:36 Duration
Lecture 22 Model 4 Plotting and visually exploring different data inputs 00:07:32 Duration
Lecture 23 Crafting multi-input fast loading tf 00:08:41 Duration
Lecture 24 Model 4 Building, fitting and evaluating a hybrid embedding model 00:13:18 Duration
Lecture 25 Model 5 Adding positional embeddings via feature engineering (overview) 00:07:18 Duration
Lecture 26 Encoding the line number feature to used with Model 5 00:12:26 Duration
Lecture 27 Encoding the total lines feature to be used with Model 5 00:07:56 Duration
Lecture 28 Model 5 Building the foundations of a tribrid embedding model 00:09:19 Duration
Lecture 29 Model 5 Completing the build of a tribrid embedding model for sequences 00:14:09 Duration
Lecture 30 Visually inspecting the architecture of our tribrid embedding model 00:10:25 Duration
Lecture 31 Creating multi-level data input pipelines for Model 5 with the tf 00:09:00 Duration
Lecture 32 Bringing SkimLit to life!!! (fitting and evaluating Model 5) 00:10:35 Duration
Lecture 33 Comparing the performance of all of our modelling experiments 00:09:36 Duration
Lecture 34 Saving, loading & testing our best performing model 00:07:49 Duration
Lecture 35 Congratulations and your challenge before heading to the next module 00:12:34 Duration
Lecture 36 Milestone Project 2 (SkimLit) challenge, exercises and extra-curriculum

Section 12 : Time Series fundamentals in TensorFlow + Milestone Project 3 BitPredict
Lecture 1 Welcome to time series fundamentals with TensorFlow + Milestone Project 3!
Lecture 2 Example forecasting problems in daily life 00:04:52 Duration
Lecture 3 What can be forecast 00:07:58 Duration
Lecture 4 What we're going to cover (broadly) 00:02:35 Duration
Lecture 5 Time series forecasting inputs and outputs 00:08:56 Duration
Lecture 6 Downloading and inspecting our Bitcoin historical dataset 00:14:58 Duration
Lecture 7 Visualizing our Bitcoin historical data with pandas 00:04:53 Duration
Lecture 8 Reading in our Bitcoin data with Python's CSV module 00:10:58 Duration
Lecture 9 Creating train and test splits for time series (the wrong way) 00:08:37 Duration
Lecture 10 Creating train and test splits for time series (the right way) 00:07:12 Duration
Lecture 11 Creating a plotting function to visualize our time series data 00:07:57 Duration
Lecture 12 Model 0 Making and visualizing a naive forecast model 00:12:16 Duration
Lecture 13 Implementing MASE with TensorFlow 00:09:38 Duration
Lecture 14 Discussing the use of windows and horizons in time series data 00:07:50 Duration
Lecture 15 Creating a function to make predictions with our trained models 00:14:03 Duration
Lecture 16 Model 3 Visualizing the results 00:08:44 Duration
Lecture 17 Comparing our modelling experiments so far and discussing autocorrelation 00:09:44 Duration
Lecture 18 Preparing data for building a Conv1D model 00:13:21 Duration
Lecture 19 Preparing our multivariate time series for a model 00:13:37 Duration
Lecture 20 Model 7 Setting up hyperparameters for the N-BEATS algorithm 00:08:51 Duration
Lecture 21 Model 7 Getting ready for residual connections 00:12:56 Duration
Lecture 22 Model 8 Ensemble model overview 00:04:44 Duration
Lecture 23 Model 8 Building, compiling and fitting an ensemble of models 00:20:04 Duration
Lecture 24 Getting the upper and lower bounds of our prediction intervals 00:07:57 Duration
Lecture 25 Plotting the prediction intervals of our ensemble model prediction 00:13:03 Duration
Lecture 26 Model 9 Creating a function to make forecasts into the future
Lecture 27 Model 9 Plotting our model's future forecasts 00:13:09 Duration
Lecture 28 Model 10 Introducing the turkey problem and making data for it 00:14:15 Duration
Lecture 29 TensorFlow Time Series Fundamentals Challenge and Extra Resources

Section 13 : Passing the TensorFlow Developer Certificate Exam
Lecture 1 Get ready to be TensorFlow Developer Certified!
Lecture 2 What is the TensorFlow Developer Certification 00:05:29 Duration
Lecture 3 Why the TensorFlow Developer Certification 00:06:57 Duration
Lecture 4 How to prepare (your brain) for the TensorFlow Developer Certification 00:08:14 Duration
Lecture 5 How to prepare (your computer) for the TensorFlow Developer Certification 00:12:43 Duration
Lecture 6 What to do after the TensorFlow Developer Certification exam 00:02:14 Duration

Section 14 : Where To Go From Here
Lecture 1 Become An Alumni
Lecture 2 About Proctor Testing
Lecture 3 About Certification

Section 15 : Appendix Machine Learning Primer
Lecture 1 Quick Note Upcoming Videos
Lecture 2 What is Machine Learning 00:06:52 Duration
Lecture 3 AIMachine LearningData Science 00:04:51 Duration
Lecture 4 Exercise Machine Learning Playground 00:06:16 Duration
Lecture 5 How Did We Get Here 00:06:03 Duration
Lecture 6 Exercise YouTube Recommendation Engine 00:04:25 Duration
Lecture 7 Types of Machine Learning 00:04:41 Duration
Lecture 8 Are You Getting It Yet
Lecture 9 What Is Machine Learning Round 2 00:04:45 Duration
Lecture 10 Section Review 00:01:48 Duration

Section 16 : Appendix Machine Learning and Data Science Framework
Lecture 1 Quick Note Upcoming Videos
Lecture 2 Section Overview 00:03:09 Duration
Lecture 3 Introducing Our Framework 00:02:38 Duration
Lecture 4 6 Step Machine Learning Framework 00:04:59 Duration
Lecture 5 Types of Machine Learning Problems 00:10:32 Duration
Lecture 6 Types of Data 00:04:51 Duration
Lecture 7 Types of Evaluation 00:03:31 Duration
Lecture 8 Features In Data 00:05:22 Duration
Lecture 9 Modelling - Splitting Data 00:05:58 Duration
Lecture 10 Modelling - Picking the Model 00:04:35 Duration
Lecture 11 Modelling - Tuning 00:03:17 Duration
Lecture 12 Modelling - Comparison 00:09:32 Duration
Lecture 13 Overfitting and Underfitting Definitions
Lecture 14 Experimentation 00:03:35 Duration
Lecture 15 Tools We Will Use 00:04:00 Duration
Lecture 16 Optional Elements of AI

Section 17 : Appendix Pandas for Data Analysis
Lecture 1 Quick Note Upcoming Videos
Lecture 2 Section Overview 00:02:27 Duration
Lecture 3 Downloading Workbooks and Assignments
Lecture 4 Pandas Introduction 00:04:29 Duration
Lecture 5 Series, Data Frames and CSVs 00:13:21 Duration
Lecture 6 Data from URLs
Lecture 7 Describing Data with Pandas 00:09:49 Duration
Lecture 8 Selecting and Viewing Data with Pandas 00:11:08 Duration
Lecture 9 Selecting and Viewing Data with Pandas Part 2 00:13:07 Duration
Lecture 10 Manipulating Data 00:13:57 Duration
Lecture 11 Manipulating Data 2 00:09:57 Duration
Lecture 12 Manipulating Data 3 00:10:12 Duration
Lecture 13 Assignment Pandas Practice
Lecture 14 How To Download The Course Assignments 00:07:43 Duration

Section 18 : Appendix NumPy
Lecture 1 Quick Note Upcoming Videos
Lecture 2 Section Overview 00:02:41 Duration
Lecture 3 NumPy Introduction 00:05:18 Duration
Lecture 4 Quick Note Correction In Next Video
Lecture 5 NumPy DataTypes and Attributes 00:14:06 Duration
Lecture 6 Creating NumPy Arrays 00:09:22 Duration
Lecture 7 NumPy Random Seed 00:07:17 Duration
Lecture 8 Viewing Arrays and Matrices 00:09:35 Duration
Lecture 9 Manipulating Arrays 00:11:32 Duration
Lecture 10 Manipulating Arrays 2 00:09:44 Duration
Lecture 11 Standard Deviation and Variance 00:07:10 Duration
Lecture 12 mp4 00:07:27 Duration
Lecture 13 Dot Product vs Element Wise 00:11:45 Duration
Lecture 14 Exercise Nut Butter Store Sales 00:13:04 Duration
Lecture 15 Comparison Operators 00:03:34 Duration
Lecture 16 Sorting Arrays 00:06:20 Duration
Lecture 17 Turn Images Into NumPy Arrays 00:07:37 Duration
Lecture 18 Assignment NumPy Practice
Lecture 19 Optional Extra NumPy resources