TensorFlow Developer Certificate in 2021: Zero to Mastery
Learn TensorFlow. Pass the TensorFlow Developer Certificate Exam. Get Hired as a TensorFlow developer. This course will take you from a TensorFlow beginner to being part of Google's Certification Network.
What you'll learn
- ✓Learn to pass Google's official TensorFlow Developer Certificate exam (and add it to your resume)
- ✓Complete access to ALL interactive notebooks and ALL course slides as downloadable guides
- ✓Understand how to integrate Machine Learning into tools and applications
- ✓Build image recognition, object detection, text recognition algorithms with deep neural networks and convolutional neural networks
- ✓Applying Deep Learning for Time Series Forecasting
- ✓Be recognized as a top candidate for recruiters seeking TensorFlow developers
- ✓Build TensorFlow models using Computer Vision, Convolutional Neural Networks and Natural Language Processing
- ✓Increase your skills in Machine Learning and Deep Learning
- ✓Learn to build all types of Machine Learning Models using the latest TensorFlow 2
- ✓Using real-world images in different shapes and sizes to visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy
- ✓Gain the skills you need to become a TensorFlow Certified Developer
Meet your instructor
Hi! I'm Daniel.
Machine Learning Engineer and Instructor
Daniel Bourke is a self-taught Machine Learning Engineer who has worked at one of Australia's fastest-growing artificial intelligence agencies, Max Kelsen, where he worked on machine learning and data problems across a wide range of industries.
He knows what it's like to try and learn a new topic, online and on your own. So he pours his soul into making sure his courses are as accessible as possible and takes complicated topics and explains them in an entertaining, yet simple and educative way.
Don't take our word for it
Seth Johnson
Thank you so much! This is an amazing course. I just passed my exam and I couldn't have done it without you. I had 3 calls on job offers today in Machine Learning! I would recommend this A+ course to anyone who wants to sharpen their skills and stand out.
Subhabrata Nath
This course is far good from any others, and I am telling this from personal experience. I have watched lots of videos about Deep Learning, but here you will get knowledge along with inspiration to write code as much as possible, and this is all that matters.
Krishna
This is an excellent course. I have taken ML classes before, but it was extremely beneficial to go through this tensorflow course. I got something practical that I could apply to datasets. After half way through this course, I was able to apply the knowledge towards Kaggle datasets and solve some problems. This course gave me the tools and confidence to start working on reviewing datasets and allowed me to focus on understanding the data.
Sha Brown
Daniel is such as an excellent instructor - the kind that I wish I had when I first studied Machine Learning. He built the course layer upon layer so that you will have a strong foundation to understand more difficult concepts. Throughout the course he also showed you his own thought process and approach towards solving problems. Thanks to Daniel, I now think more like a machine learning engineer and I am better at solving problems with Tensorflow as learning goes on.
Joel Joseph
Best course to practically learn Deep Learning and Tensorflow. I have done a couple of ZTM courses and it is the best resource online to learn computer science fundamentals, Web Development, Machine Learning, etc. The instructors design the course such that, after the course you are able to use those technologies in your projects. You really go from zero to mastery!
Blazey
This course is just plain amazing. I can't stress it enough. Danial focuses on the code and the practical aspects of Deep Learning rather than go deep (pun intended) in the theory. His way of teaching is unparalleled, and listening to him always brings a smile on my face. His approach to learning Deep Learning is revolutionary and I would wish him the best of luck for all of his future courses. Have a great day and keep coding!
Why Zero To Mastery is right for you
With so many online resources available, it can be paralyzing not only figuring out where to start but more importantly which courses will actually teach you the skills you need to get hired.
That’s why the Zero To Mastery Academy exists, to provide industry-leading courses and content to teach you the relevant skills you need to advance your career and get you hired at some of the top companies in the world.
Join now to get complete access to this course and all others for only $23/month.
Course Curriculum
We want you to make sure this course is a good fit for you. So start learning for free right now by clicking the PREVIEW links below.
Example Curriculum
- What is deep learning? (4:38)
- Why use deep learning? (9:38)
- What are neural networks? (10:26)
- What is deep learning already being used for? (8:36)
- What is and why use TensorFlow? (7:56)
- What is a Tensor? (3:37)
- What we're going to cover throughout the course (4:29)
- How to approach this course (5:33)
- Need A Refresher?
- Creating your first tensors with TensorFlow and tf.constant() (18:45)
- Creating tensors with TensorFlow and tf.Variable() (7:07)
- Creating random tensors with TensorFlow (9:40)
- Shuffling the order of tensors (9:40)
- Creating tensors from NumPy arrays (11:55)
- Getting information from your tensors (tensor attributes) (11:57)
- Indexing and expanding tensors (12:33)
- Manipulating tensors with basic operations (5:34)
- Matrix multiplication with tensors part 1 (11:53)
- Matrix multiplication with tensors part 2 (13:29)
- Matrix multiplication with tensors part 3 (10:03)
- Changing the datatype of tensors (6:55)
- Tensor aggregation (finding the min, max, mean & more) (9:49)
- Tensor troubleshooting example (updating tensor datatypes) (6:13)
- Finding the positional minimum and maximum of a tensor (argmin and argmax) (9:31)
- Squeezing a tensor (removing all 1-dimension axes) (2:59)
- One-hot encoding tensors (5:46)
- Trying out more tensor math operations (4:47)
- Exploring TensorFlow and NumPy's compatibility (5:43)
- Making sure our tensor operations run really fast on GPUs (10:19)
- TensorFlow Fundamentals challenge, exercises & extra-curriculum
- Python + Machine Learning Monthly
- Endorsements On LinkedIn
- Introduction to Neural Network Regression with TensorFlow (7:33)
- Inputs and outputs of a neural network regression model (8:59)
- Anatomy and architecture of a neural network regression model (7:55)
- Creating sample regression data (so we can model it) (12:46)
- The major steps in modelling with TensorFlow (20:15)
- Steps in improving a model with TensorFlow part 1 (6:02)
- Steps in improving a model with TensorFlow part 2 (9:25)
- Steps in improving a model with TensorFlow part 3 (12:33)
- Evaluating a TensorFlow model part 1 ("visualise, visualise, visualise") (7:24)
- Evaluating a TensorFlow model part 2 (the three datasets) (11:01)
- Evaluating a TensorFlow model part 3 (getting a model summary) (17:18)
- Evaluating a TensorFlow model part 4 (visualising a model's layers) (7:14)
- Evaluating a TensorFlow model part 5 (visualising a model's predictions) (9:16)
- Evaluating a TensorFlow model part 6 (common regression evaluation metrics) (8:05)
- Evaluating a TensorFlow regression model part 7 (mean absolute error) (5:52)
- Evaluating a TensorFlow regression model part 7 (mean square error) (3:18)
- Setting up TensorFlow modelling experiments part 1 (start with a simple model) (13:50)
- Setting up TensorFlow modelling experiments part 2 (increasing complexity) (11:29)
- Comparing and tracking your TensorFlow modelling experiments (10:20)
- How to save a TensorFlow model (8:19)
- How to load and use a saved TensorFlow model (10:15)
- (Optional) How to save and download files from Google Colab (6:18)
- Putting together what we've learned part 1 (preparing a dataset) (13:31)
- Putting together what we've learned part 2 (building a regression model) (13:20)
- Putting together what we've learned part 3 (improving our regression model) (15:47)
- Preprocessing data with feature scaling part 1 (what is feature scaling?) (9:34)
- Preprocessing data with feature scaling part 2 (normalising our data) (10:57)
- Preprocessing data with feature scaling part 3 (fitting a model on scaled data) (7:40)
- TensorFlow Regression challenge, exercises & extra-curriculum
- Introduction to neural network classification in TensorFlow (8:25)
- Example classification problems (and their inputs and outputs) (6:38)
- Input and output tensors of classification problems (6:21)
- Typical architecture of neural network classification models with TensorFlow (9:36)
- Creating and viewing classification data to model (11:34)
- Checking the input and output shapes of our classification data (4:38)
- Building a not very good classification model with TensorFlow (12:10)
- Trying to improve our not very good classification model (9:13)
- Creating a function to view our model's not so good predictions (15:08)
- Make our poor classification model work for a regression dataset (12:18)
- Non-linearity part 1: Straight lines and non-straight lines (9:38)
- Non-linearity part 2: Building our first neural network with non-linearity (5:47)
- Non-linearity part 3: Upgrading our non-linear model with more layers (10:18)
- Non-linearity part 4: Modelling our non-linear data once and for all (8:37)
- Non-linearity part 5: Replicating non-linear activation functions from scratch (14:26)
- Getting great results in less time by tweaking the learning rate (14:47)
- Using the TensorFlow History object to plot a model's loss curves (6:11)
- Using callbacks to find a model's ideal learning rate (17:32)
- Training and evaluating a model with an ideal learning rate (9:20)
- Introducing more classification evaluation methods (6:04)
- Finding the accuracy of our classification model (4:17)
- Creating our first confusion matrix (to see where our model is getting confused) (8:27)
- Making our confusion matrix prettier (14:00)
- Putting things together with multi-class classification part 1: Getting the data (10:37)
- Multi-class classification part 2: Becoming one with the data (7:07)
- Multi-class classification part 3: Building a multi-class classification model (15:38)
- Multi-class classification part 4: Improving performance with normalisation (12:43)
- Multi-class classification part 5: Comparing normalised and non-normalised data (4:13)
- Multi-class classification part 6: Finding the ideal learning rate (10:38)
- Multi-class classification part 7: Evaluating our model (13:16)
- Multi-class classification part 8: Creating a confusion matrix (4:26)
- Multi-class classification part 9: Visualising random model predictions (10:42)
- What "patterns" is our model learning? (15:33)
- TensorFlow classification challenge, exercises & extra-curriculum
- Introduction to Computer Vision with TensorFlow (9:36)
- Introduction to Convolutional Neural Networks (CNNs) with TensorFlow (7:59)
- Downloading an image dataset for our first Food Vision model (8:27)
- Becoming One With Data (5:05)
- Becoming One With Data Part 2 (12:26)
- Becoming One With Data Part 3 (4:22)
- Building an end to end CNN Model (18:17)
- Using a GPU to run our CNN model 5x faster (9:17)
- Trying a non-CNN model on our image data (8:51)
- Improving our non-CNN model by adding more layers (9:52)
- Breaking our CNN model down part 1: Becoming one with the data (9:03)
- Breaking our CNN model down part 2: Preparing to load our data (11:46)
- Breaking our CNN model down part 3: Loading our data with ImageDataGenerator (9:54)
- Breaking our CNN model down part 4: Building a baseline CNN model (8:02)
- Breaking our CNN model down part 5: Looking inside a Conv2D layer (15:20)
- Breaking our CNN model down part 6: Compiling and fitting our baseline CNN (7:14)
- Breaking our CNN model down part 7: Evaluating our CNN's training curves (11:45)
- Breaking our CNN model down part 8: Reducing overfitting with Max Pooling (13:40)
- Breaking our CNN model down part 9: Reducing overfitting with data augmentation (6:52)
- Breaking our CNN model down part 10: Visualizing our augmented data (15:04)
- Breaking our CNN model down part 11: Training a CNN model on augmented data (8:49)
- Breaking our CNN model down part 12: Discovering the power of shuffling data (10:01)
- Breaking our CNN model down part 13: Exploring options to improve our model (5:21)
- Downloading a custom image to make predictions on (4:54)
- Writing a helper function to load and preprocessing custom images (10:00)
- Making a prediction on a custom image with our trained CNN (10:08)
- Multi-class CNN's part 1: Becoming one with the data (14:59)
- Multi-class CNN's part 2: Preparing our data (turning it into tensors) (6:38)
- Multi-class CNN's part 3: Building a multi-class CNN model (7:24)
- Multi-class CNN's part 4: Fitting a multi-class CNN model to the data (6:02)
- Multi-class CNN's part 5: Evaluating our multi-class CNN model (4:51)
- Multi-class CNN's part 6: Trying to fix overfitting by removing layers (12:19)
- Multi-class CNN's part 7: Trying to fix overfitting with data augmentation (11:45)
- Multi-class CNN's part 8: Things you could do to improve your CNN model (4:23)
- Multi-class CNN's part 9: Making predictions with our model on custom images (9:22)
- Saving and loading our trained CNN model (6:21)
- TensorFlow computer vision and CNNs challenge, exercises & extra-curriculum
- What is and why use transfer learning? (10:12)
- Downloading and preparing data for our first transfer learning model (14:39)
- Introducing Callbacks in TensorFlow and making a callback to track our models (10:01)
- Exploring the TensorFlow Hub website for pretrained models (9:51)
- Building and compiling a TensorFlow Hub feature extraction model (14:00)
- Blowing our previous models out of the water with transfer learning (9:13)
- Plotting the loss curves of our ResNet feature extraction model (7:35)
- Building and training a pre-trained EfficientNet model on our data (9:42)
- Different Types of Transfer Learning (11:40)
- Comparing Our Model's Results (15:16)
- TensorFlow Transfer Learning Part 1 challenge, exercises & extra-curriculum
- Introduction to Transfer Learning in TensorFlow Part 2: Fine-tuning (6:16)
- Importing a script full of helper functions (and saving lots of space) (7:35)
- Downloading and turning our images into a TensorFlow BatchDataset (15:38)
- Discussing the four (actually five) modelling experiments we're running (2:15)
- Comparing the TensorFlow Keras Sequential API versus the Functional API (2:34)
- Creating our first model with the TensorFlow Keras Functional API (11:38)
- Compiling and fitting our first Functional API model (10:53)
- Getting a feature vector from our trained model (13:39)
- Drilling into the concept of a feature vector (a learned representation) (3:43)
- Downloading and preparing the data for Model 1 (1 percent of training data) (9:51)
- Building a data augmentation layer to use inside our model (12:06)
- Visualising what happens when images pass through our data augmentation layer (10:55)
- Building Model 1 (with a data augmentation layer and 1% of training data) (15:55)
- Building Model 2 (with a data augmentation layer and 10% of training data) (16:37)
- Creating a ModelCheckpoint to save our model's weights during training (7:25)
- Fitting and evaluating Model 2 (and saving its weights using ModelCheckpoint) (7:14)
- Loading and comparing saved weights to our existing trained Model 2 (7:17)
- Preparing Model 3 (our first fine-tuned model) (20:26)
- Fitting and evaluating Model 3 (our first fine-tuned model) (7:45)
- Comparing our model's results before and after fine-tuning (10:26)
- Downloading and preparing data for our biggest experiment yet (Model 4) (6:24)
- Preparing our final modelling experiment (Model 4) (12:00)
- Fine-tuning Model 4 on 100% of the training data and evaluating its results (10:19)
- Comparing our modelling experiment results in TensorBoard (10:46)
- How to view and delete previous TensorBoard experiments (2:04)
- Transfer Learning in TensorFlow Part 2 challenge, exercises and extra-curriculum
- Introduction to Transfer Learning Part 3: Scaling Up (6:19)
- Getting helper functions ready and downloading data to model (13:34)
- Outlining the model we're going to build and building a ModelCheckpoint callback (5:38)
- Creating a data augmentation layer to use with our model (4:39)
- Creating a headless EfficientNetB0 model with data augmentation built in (8:58)
- Fitting and evaluating our biggest transfer learning model yet (7:56)
- Unfreezing some layers in our base model to prepare for fine-tuning (11:28)
- Fine-tuning our feature extraction model and evaluating its performance (8:23)
- Saving and loading our trained model (6:25)
- Downloading a pretrained model to make and evaluate predictions with (6:34)
- Making predictions with our trained model on 25,250 test samples (12:46)
- Unravelling our test dataset for comparing ground truth labels to predictions (6:05)
- Confirming our model's predictions are in the same order as the test labels (5:17)
- Creating a confusion matrix for our model's 101 different classes (12:07)
- Evaluating every individual class in our dataset (14:16)
- Plotting our model's F1-scores for each separate class (7:36)
- Creating a function to load and prepare images for making predictions (12:08)
- Making predictions on our test images and evaluating them (16:06)
- Discussing the benefits of finding your model's most wrong predictions (6:09)
- Writing code to uncover our model's most wrong predictions (11:16)
- Plotting and visualizing the samples our model got most wrong (10:36)
- Making predictions on and plotting our own custom images (9:49)
- Transfer Learning in TensorFlow Part 3 challenge, exercises and extra-curriculum
- Introduction to Milestone Project 1: Food Vision Big™ (5:44)
- Making sure we have access to the right GPU for mixed precision training (10:17)
- Getting helper functions ready (3:06)
- Introduction to TensorFlow Datasets (TFDS) (12:03)
- Exploring and becoming one with the data (Food101 from TensorFlow Datasets) (15:56)
- Creating a preprocessing function to prepare our data for modelling (15:50)
- Batching and preparing our datasets (to make them run fast) (13:47)
- Exploring what happens when we batch and prefetch our data (6:49)
- Creating modelling callbacks for our feature extraction model (7:14)
- Note: Mixed Precision producing errors for TensorFlow 2.5+
- Turning on mixed precision training with TensorFlow (10:05)
- Creating a feature extraction model capable of using mixed precision training (12:42)
- Checking to see if our model is using mixed precision training layer by layer (7:56)
- Training and evaluating a feature extraction model (Food Vision Big™) (10:19)
- Introducing your Milestone Project 1 challenge: build a model to beat DeepFood (7:47)
- Milestone Project 1: Food Vision Big™, exercises and extra-curriculum
- Welcome to natural language processing with TensorFlow!
- Introduction to Natural Language Processing (NLP) and Sequence Problems (12:51)
- Example NLP inputs and outputs (7:22)
- The typical architecture of a Recurrent Neural Network (RNN) (9:03)
- Preparing a notebook for our first NLP with TensorFlow project (8:52)
- Becoming one with the data and visualizing a text dataset (16:41)
- Splitting data into training and validation sets (6:26)
- Converting text data to numbers using tokenisation and embeddings (overview) (9:22)
- Setting up a TensorFlow TextVectorization layer to convert text to numbers (17:10)
- Mapping the TextVectorization layer to text data and turning it into numbers (11:02)
- Creating an Embedding layer to turn tokenised text into embedding vectors (12:27)
- Discussing the various modelling experiments we're going to run (8:57)
- Model 0: Building a baseline model to try and improve upon (9:25)
- Creating a function to track and evaluate our model's results (12:14)
- Model 1: Building, fitting and evaluating our first deep model on text data (20:51)
- Visualizing our model's learned word embeddings with TensorFlow's projector tool (20:43)
- High-level overview of Recurrent Neural Networks (RNNs) + where to learn more (9:34)
- Model 2: Building, fitting and evaluating our first TensorFlow RNN model (LSTM) (18:16)
- Model 3: Building, fitting and evaluating a GRU-cell powered RNN (16:56)
- Model 4: Building, fitting and evaluating a bidirectional RNN model (19:34)
- Discussing the intuition behind Conv1D neural networks for text and sequences (19:31)
- Model 5: Building, fitting and evaluating a 1D CNN for text (9:57)
- Using TensorFlow Hub for pretrained word embeddings (transfer learning for NLP) (13:45)
- Model 6: Building, training and evaluating a transfer learning model for NLP (10:45)
- Preparing subsets of data for model 7 (same as model 6 but 10% of data) (10:52)
- Model 7: Building, training and evaluating a transfer learning model on 10% data (10:04)
- Fixing our data leakage issue with model 7 and retraining it (13:42)
- Comparing all our modelling experiments evaluation metrics (13:14)
- Uploading our model's training logs to TensorBoard and comparing them (11:14)
- Saving and loading in a trained NLP model with TensorFlow (10:25)
- Downloading a pretrained model and preparing data to investigate predictions (13:24)
- Visualizing our model's most wrong predictions (8:28)
- Making and visualizing predictions on the test dataset (8:27)
- Understanding the concept of the speed/score tradeoff (15:01)
- NLP Fundamentals in TensorFlow challenge, exercises and extra-curriculum
- Introduction to Milestone Project 2: SkimLit (14:20)
- What we're going to cover in Milestone Project 2 (NLP for medical abstracts) (7:22)
- SkimLit inputs and outputs (11:02)
- Setting up our notebook for Milestone Project 2 (getting the data) (14:58)
- Visualizing examples from the dataset (becoming one with the data) (13:18)
- Writing a preprocessing function to structure our data for modelling (19:50)
- Performing visual data analysis on our preprocessed text (7:55)
- Turning our target labels into numbers (ML models require numbers) (13:15)
- Model 0: Creating, fitting and evaluating a baseline model for SkimLit (9:25)
- Preparing our data for deep sequence models (9:55)
- Creating a text vectoriser to map our tokens (text) to numbers (14:07)
- Creating a custom token embedding layer with TensorFlow (9:14)
- Creating fast loading dataset with the TensorFlow tf.data API (9:49)
- Model 1: Building, fitting and evaluating a Conv1D with token embeddings (17:21)
- Preparing a pretrained embedding layer from TensorFlow Hub for Model 2 (10:53)
- Model 2: Building, fitting and evaluating a Conv1D model with token embeddings (11:30)
- Creating a character-level tokeniser with TensorFlow's TextVectorization layer (23:24)
- Creating a character-level embedding layer with tf.keras.layers.Embedding (7:44)
- Model 3: Building, fitting and evaluating a Conv1D model on character embeddings (13:45)
- Discussing how we're going to build Model 4 (character + token embeddings) (6:04)
- Model 4: Building a multi-input model (hybrid token + character embeddings) (15:36)
- Model 4: Plotting and visually exploring different data inputs (7:32)
- Crafting multi-input fast loading tf.data datasets for Model 4 (8:41)
- Model 4: Building, fitting and evaluating a hybrid embedding model (13:18)
- Model 5: Adding positional embeddings via feature engineering (overview) (7:18)
- Encoding the line number feature to used with Model 5 (12:25)
- Encoding the total lines feature to be used with Model 5 (7:56)
- Model 5: Building the foundations of a tribrid embedding model (9:19)
- Model 5: Completing the build of a tribrid embedding model for sequences (14:08)
- Visually inspecting the architecture of our tribrid embedding model (10:25)
- Creating multi-level data input pipelines for Model 5 with the tf.data API (9:00)
- Bringing SkimLit to life!!! (fitting and evaluating Model 5) (10:35)
- Comparing the performance of all of our modelling experiments (9:36)
- Saving, loading & testing our best performing model (7:48)
- Congratulations and your challenge before heading to the next module (12:33)
- Milestone Project 2 (SkimLit) challenge, exercises and extra-curriculum
- Welcome to time series fundamentals with TensorFlow + Milestone Project 3!
- Introduction to Milestone Project 3 (BitPredict) & where you can get help (3:53)
- What is a time series problem and example forecasting problems at Uber (7:45)
- Example forecasting problems in daily life (4:52)
- What can be forecast? (7:57)
- What we're going to cover (broadly) (2:35)
- Time series forecasting inputs and outputs (8:55)
- Downloading and inspecting our Bitcoin historical dataset (14:58)
- Different kinds of time series patterns & different amounts of feature variables (7:39)
- Visualizing our Bitcoin historical data with pandas (4:52)
- Reading in our Bitcoin data with Python's CSV module (10:58)
- Creating train and test splits for time series (the wrong way) (8:37)
- Creating train and test splits for time series (the right way) (7:12)
- Creating a plotting function to visualize our time series data (7:57)
- Discussing the various modelling experiments were going to be running (9:11)
- Model 0: Making and visualizing a naive forecast model (12:16)
- Discussing some of the most common time series evaluation metrics (11:11)
- Implementing MASE with TensorFlow (9:38)
- Creating a function to evaluate our model's forecasts with various metrics (10:11)
- Discussing other non-TensorFlow kinds of time series forecasting models (5:06)
- Formatting data Part 2: Creating a function to label our windowed time series (13:01)
- Discussing the use of windows and horizons in time series data (7:50)
- Writing a preprocessing function to turn time series data into windows & labels (23:35)
- Turning our windowed time series data into training and test sets (10:01)
- Creating a modelling checkpoint callback to save our best performing model (7:25)
- Model 1: Building, compiling and fitting a deep learning model on Bitcoin data (16:58)
- Creating a function to make predictions with our trained models (14:02)
- Model 2: Building, fitting and evaluating a deep model with a larger window size-27 (17:43)
- Model 3: Building, fitting and evaluating a model with a larger horizon size (13:15)
- Adjusting the evaluation function to work for predictions with larger horizons (8:34)
- Model 3: Visualizing the results (8:44)
- Comparing our modelling experiments so far and discussing autocorrelation (9:44)
- Preparing data for building a Conv1D model (13:21)
- Model 4: Building, fitting and evaluating a Conv1D model on our Bitcoin data (14:51)
- Model 5: Building, fitting and evaluating a LSTM (RNN) model on our Bitcoin data (16:05)
- Investigating how to turn our univariate time series into multivariate (13:52)
- Creating and plotting a multivariate time series with BTC price and block reward (12:12)
- Preparing our multivariate time series for a model (13:37)
- Model 6: Building, fitting and evaluating a multivariate time series model (9:25)
- Model 7: Discussing what we're going to be doing with the N-BEATS algorithm (9:39)
- Model 7: Replicating the N-BEATS basic block with TensorFlow layer subclassing (18:38)
- Model 7: Testing our N-BEATS block implementation with dummy data inputs (15:02)
- Model 7: Creating a performant data pipeline for the N-BEATS model with tf.data (14:09)
- Model 7: Setting up hyperparameters for the N-BEATS algorithm (8:50)
- Model 7: Getting ready for residual connections (12:55)
- Model 7: Outlining the steps we're going to take to build the N-BEATS model (10:05)
- Model 7: Putting together the pieces of the puzzle of the N-BEATS model (22:22)
- Model 7: Plotting the N-BEATS algorithm we've created and admiring its beauty (6:46)
- Model 8: Ensemble model overview (4:43)
- Model 8: Building, compiling and fitting an ensemble of models (20:04)
- Model 8: Making and evaluating predictions with our ensemble model (16:09)
- Discussing the importance of prediction intervals in forecasting (12:56)
- Getting the upper and lower bounds of our prediction intervals (7:57)
- Plotting the prediction intervals of our ensemble model predictions (13:02)
- (Optional) Discussing the types of uncertainty in machine learning (13:41)
- Model 9: Preparing data to create a model capable of predicting into the future (8:24)
- Model 9: Building, compiling and fitting a future predictions model (5:01)
- Model 9: Discussing what's required for our model to make future predictions (8:30)
- Model 9: Creating a function to make forecasts into the future (12:08)
- Model 9: Plotting our model's future forecasts (13:09)
- Model 10: Introducing the turkey problem and making data for it (14:15)
- Model 10: Building a model to predict on turkey data (why forecasting is BS) (13:38)
- Comparing the results of all of our models and discussing where to go next (12:59)
- TensorFlow Time Series Fundamentals Challenge and Extra Resources
- Get ready to be TensorFlow Developer Certified!
- What is the TensorFlow Developer Certification? (5:28)
- Why the TensorFlow Developer Certification? (6:57)
- How to prepare (your brain) for the TensorFlow Developer Certification (8:14)
- How to prepare (your computer) for the TensorFlow Developer Certification (12:43)
- What to do after the TensorFlow Developer Certification exam (2:13)
- Quick Note: Upcoming Videos
- What is Machine Learning? (6:52)
- AI/Machine Learning/Data Science (4:51)
- Exercise: Machine Learning Playground (6:16)
- How Did We Get Here? (6:03)
- Exercise: YouTube Recommendation Engine (4:24)
- Types of Machine Learning (4:41)
- Are You Getting It Yet?
- What Is Machine Learning? Round 2 (4:44)
- Section Review (1:48)
- Quick Note: Upcoming Videos
- Section Overview (3:08)
- Introducing Our Framework (2:38)
- 6 Step Machine Learning Framework (4:59)
- Types of Machine Learning Problems (10:32)
- Types of Data (4:50)
- Types of Evaluation (3:31)
- Features In Data (5:22)
- Modelling - Splitting Data (5:58)
- Modelling - Picking the Model (4:35)
- Modelling - Tuning (3:17)
- Modelling - Comparison (9:32)
- Overfitting and Underfitting Definitions
- Experimentation (3:35)
- Tools We Will Use (3:59)
- Optional: Elements of AI(document)
- Quick Note: Upcoming Videos
- Section Overview (2:27)
- Downloading Workbooks and Assignments
- Pandas Introduction (4:29)
- Series, Data Frames and CSVs (13:21)
- Data from URLs
- Describing Data with Pandas (9:48)
- Selecting and Viewing Data with Pandas (11:08)
- Selecting and Viewing Data with Pandas Part 2 (13:06)
- Manipulating Data (13:56)
- Manipulating Data 2 (9:56)
- Manipulating Data 3 (10:12)
- Assignment: Pandas Practice
- How To Download The Course Assignments (7:43)
- Quick Note: Upcoming Videos
- Section Overview (2:40)
- NumPy Introduction (5:17)
- Quick Note: Correction In Next Video
- NumPy DataTypes and Attributes (14:05)
- Creating NumPy Arrays (9:22)
- NumPy Random Seed (7:17)
- Viewing Arrays and Matrices (9:35)
- Manipulating Arrays (11:31)
- Manipulating Arrays 2 (9:44)
- Standard Deviation and Variance (7:10)
- Reshape and Transpose (7:26)
- Dot Product vs Element Wise (11:45)
- Exercise: Nut Butter Store Sales (13:04)
- Comparison Operators (3:33)
- Sorting Arrays (6:19)
- Turn Images Into NumPy Arrays (7:37)
- Assignment: NumPy Practice
- Optional: Extra NumPy resources
Course Details
Learn TensorFlow, pass the TensorFlow Developer Certificate exam and get hired as a Machine Learning Engineer making $100,000+ a year. Taught by TensorFlow Certified Expert, Daniel Bourke, this course will take you step-by-step from an absolute beginner with TensorFlow to becoming part of Google's TensorFlow Certification Network.
TensorFlow developers earn US$148,000 on average with some earning over US$200,000 according to 2021 statistics from ZipRecruiter. By passing the exam and getting the TensorFlow Developer Certificate (officially recognized by Google), you will be part of Google's TensorFlow Developer Network where recruiters are able to find you.
Graduates of Zero To Mastery are now working at Google, Tesla, Amazon, Apple, IBM, JP Morgan, Facebook, Shopify + other top tech companies. This could be you.
By enrolling today, you’ll also get to join our exclusive live online community classroom to learn alongside thousands of students, alumni, mentors, TAs and Instructors. Most importantly, you will be learning TensorFlow from an industry expert with actual real-world experience and is TensorFlow certified.
The goal of this course is to teach you all the skills necessary for you to pass this exam and get your TensorFlow Certification so you can display it on your resume, LinkedIn, Github and other social media platforms to make you stand out as a top candidate for recruiters looking for TensorFlow developers.
Here is a full course breakdown of everything you will learn:
This TensorFlow course is very hands-on and project based. You won't just be staring at us teach and code. We'll leave that for other tutorials and courses.
You will actually be running experiments, doing exercises and building real-world machine learning models and projects to mimic real life scenarios. We will also show you what the TensorFlow exam will look like for you. By the end of it all, you will develop the skillset needed to develop modern deep learning solutions that big tech companies encounter.
Fair warning, this course is very comprehensive, but don't be intimidated, we will teach you everything from scratch!
0 — TensorFlow Fundamentals
- Introduction to tensors (creating tensors)
- Getting information from tensors (tensor attributes)
- Manipulating tensors (tensor operations)
- Tensors and NumPy
- Using @tf.function (a way to speed up your regular Python functions)
- Using GPUs with TensorFlow
1 — Neural Network Regression with TensorFlow
- Build TensorFlow sequential models with multiple layers
- Prepare data for use with a machine learning model
- Learn the different components which make up a deep learning model (loss function, architecture, optimization function)
- Learn how to diagnose a regression problem (predicting a number) and build a neural network for it
2 — Neural Network Classification with TensorFlow
- Learn how to diagnose a classification problem (predicting whether something is one thing or another)
- Build, compile & train machine learning classification models using TensorFlow
- Build and train models for binary and multi-class classification
- Plot modelling performance metrics against each other
- Match input (training data shape) and output shapes (prediction data target)
3 — Computer Vision and Convolutional Neural Networks with TensorFlow
- Build convolutional neural networks with Conv2D and pooling layers
- Learn how to diagnose different kinds of computer vision problems
- Learn to how to build computer vision neural networks
- Learn how to use real-world images with your computer vision models
4 — Transfer Learning with TensorFlow Part 1: Feature Extraction
- Learn how to use pre-trained models to extract features from your own data
- Learn how to use TensorFlow Hub for pre-trained models
- Learn how to use TensorBoard to compare the performance of several different models
5 — Transfer Learning with TensorFlow Part 2: Fine-tuning
- Learn how to setup and run several machine learning experiments
- Learn how to use data augmentation to increase the diversity of your training data
- Learn how to fine-tune a pre-trained model to your own custom problem
- Learn how to use Callbacks to add functionality to your model during training
6 — Transfer Learning with TensorFlow Part 3: Scaling Up (Food Vision mini)
- Learn how to scale up an existing model
- Learn to how evaluate your machine learning models by finding the most wrong predictions
- Beat the original Food101 paper using only 10% of the data
7 — Milestone Project 1: Food Vision
- Combine everything you've learned in the previous 6 notebooks to build Food Vision: a computer vision model able to classify 101 different kinds of foods. Our model well and truly beats the original Food101 paper.
8 — NLP Fundamentals in TensorFlow
- Learn to:
- Preprocess natural language text to be used with a neural network
- Create word embeddings (numerical representations of text) with TensorFlow
- Build neural networks capable of binary and multi-class classification using:
- RNNs (recurrent neural networks)
- LSTMs (long short-term memory cells)
- GRUs (gated recurrent units)
- CNNs
- Learn how to evaluate your NLP models
- Replicate a the model which powers the PubMed 200k paper to classify different sequences in PubMed medical abstracts (which can help researchers read through medical abstracts faster)
- Learn how to diagnose a time series problem (building a model to make predictions based on data across time, e.g. predicting the stock price of AAPL tomorrow)
- Prepare data for time series neural networks (features and labels)
- Understanding and using different time series evaluation methods
- MAE — mean absolute error
- Build time series forecasting models with TensorFlow
- RNNs (recurrent neural networks)
- CNNs (convolutional neural networks)
- If you've read this far, you are probably interested in the course. This last project will be good... we promise you, so see you inside the course ;)
9 — Milestone Project 2: SkimLit
10 — Time Series fundamentals in TensorFlow
11 — Milestone Project 3: (Surprise)
TensorFlow's growth and adoption is exploding which means more and more job openings are appearing for this specialized knowledge. Companies like Google, Airbnb, Uber, DeepMind, Intel, IBM, Twitter, and many others are currently powered by TensorFlow. TensorFlow is even outgrowing other popular Machine Learning tools like PyTorch in the job market.
We guarantee you this is the most comprehensive online course on passing the TensorFlow Developer Certificate and qualify you as a TensorFlow expert. So why wait? Advance your career and earn a higher salary by becoming a Google Certified Developer and adding TensorFlow to your toolkit.
Click Start Learning Now to join the Academy. We'll see you inside the course!
Answers to (at least some of) your questions
Are there any prerequisites for this course?
- No previous TensorFlow knowledge required. Basic understanding of Machine Learning is helpful but if you've taken Daniel's Machine Learning course (part of the ZTM Academy), you're all set!
- Mac / Windows / Linux - any operating systems will work
Why should I learn TensorFlow and get the TensorFlow Developer Certificate?
- Lots of jobs available: Used by major companies like Google, Airbnb, Uber, DeepMind, Intel, IBM, Twitter means there is huge job demand for TensorFlow developers. TensorFlow is outgrowing other popular ML tools like PyTorch in the job market.
- High demand = High salary: Per ZipRecruiter, the avg annual salary for a TensorFlow developer in the United States is $148,508.
- Old fashioned FUN: Learning TensorFlow allows you to build deep learning models for a range of tasks such as regression, computer vision (finding patterns in images), natural language processing (finding patterns in text) and time series forecasting (predicting future trends given a range of past events). That's pretty damn awesome!
Who is this course for?
- You want a step-by-step guide to pass the TensorFlow Developer Certificate exam so that you can join Google's Certificate Network and get hired at a top company, making over $100,000 / year
- You want to be recognized as a top tier quality candidate by recruiters at leading companies
- Anyone who wants to learn TensorFlow and how to pass the TensorFlow exam from an industry expert (Daniel Bourke) who has taken and passed the exam and has actually worked in the field
- Students, developers, and data scientists who want to demonstrate practical machine learning skills by actually building and training real models using TensorFlow
- Anyone looking to expand their knowledge when it comes to AI, Machine Learning and Deep Learning
- Anyone looking to get real-world experience building TensorFlow models using Computer Vision, Convolutional Neural Networks and Natural Language Processing with the latest version of TensorFlow
Do you provide a certificate of completion?
We definitely do and they are quite nice. You will also be able to add Zero To Mastery Academy to the education section of your LinkedIn profile as well.
Can I use the course projects in my portfolio?
Yes, you’d be crazy not to! You won't just be staring at us teach. You will actually be running experiments, doing exercises and building machine learning models and projects to mimic real life scenarios.
Many of our students tell us the projects they built while following along with our courses were what got them interviews and because they built the projects themselves, they could confidently explain and walk through their work during the interview. You know what that means? Job offer!
Can I download the videos?
Definitely. You can download any and all lessons for personal use. We do everything we can to make learning easy, fun, and accessible whether that’s on your commute, on a flight or if you just have limited access to good wifi.
Can I learn TensorFlow and pass the exam with free resources?
Yes, of course you can. You can go learn all the skills you need by going through the TensorFlow documentation. In fact, when I need to practice something, I copy the documentation examples verbatim (every line of code), practice understanding it line by line, then see if I can do it myself.
However, that will likely take you a long time. This course puts you on a fast track to passing the TensorFlow exam by providing you with a clear step-by-step guide with absolutely everything you need to learn in one place.
Still have more questions specific to the Academy membership? No problem, head to the bottom of this page.
Live the life you want, starting now
Learning data science and machine learning and becoming a Machine Learning Engineer provides endless opportunities to live the life you want. Whether that’s a high paying job with a world-class tech company, working remotely or building your own apps, the ZTM Academy will equip you with the skills and knowledge to achieve your dreams.
Our courses walk you through the entire journey of starting to learn to code to having a successful career in the tech industry. Along the way, you’ll not only be supported by Daniel himself and our course TAs but also your thousands of peers in the exclusive Zero To Mastery community.
Join now to take the first step to change your life.