Join the best training ground for AI mastery and gain the skills you need to become a TensorFlow Certified Developer.
What you'll learn
Understand Deep Learning Fundamentals
Construct three different deep learning models using TensorFlow and Keras
Classify images using convolutional neural networks (CNNs) in TensorFlow.
Apply image augmentation and transfer learning to enhance model performance.
Utilize strategies to prevent overfitting, including augmentation and dropout.
Process text through tokenization and sentence vector representation.
Apply Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks to NLP tasks
Create Device-Based Models with TensorFlow Lite
Requirements
Basic knowledge of programming is recommended.
Some experience in Machine Learning is also preferable but not required.
Description
In this course you will learn everything you need to know to master the TensorFlow Developer Certification.We will start by studying Deep Learning in depth so that you can understand how artificial neural networks work and learn. And while covering the Deep Learning theory we will also build together three different Deep Learning models in TensorFlow and Keras, from scratch, step by step, and coding every single line of code together.Then, we will move on to Computer Vision, where you will learn how to classify images using convolutions with TensorFlow. You will also learn some techniques such as image augmentation and transfer learning to get even more performance in your computer vision tasks. And we will practice all this on real-world image data, while exploring strategies to prevent overfitting, including augmentation and dropout.Then, you will learn how to use JavaScript, in order to train and run inference in a browser, handle data in a browser, and even build an object classification and recognition model using a webcam.Then you will learn how to do Natural Language Processing using TensorFlow. Here we will build natural language processing systems, process text including tokenization and representing sentences as vectors, apply RNNs, GRUs, and LSTMs in TensorFlow, and train LSTMs on existing text to create original poetry and more.And finally, you will also learn how to build Device-based Models with TensorFlow Lite. In this last part we will prepare models for battery-operated devices, execute models on Android and iOS platforms, and deploy models on embedded systems like Raspberry Pi and microcontrollers.Who this course is for:The course is targeted towards AI practitioners, aspiring data scientists, Tech enthusiasts, and consultants wanting to pass the TensorFlow Developer Certification. Here's a list of who is this course for
ata Scientists who simply want to learn how to use TensorFlow at an advanced level.Data Scientists who want to pass the TensorFlow Developer Certification.AI Practitioners who want to build more powerful AI models using TensorFlow.Tech enthusiasts who are passionate about AI and want to gain real-world practical experience with TensorFlow. Course Prerequisites:Basic knowledge of programming is recommended. Some experience in Machine Learning is also preferable. However, these topics will be extensively covered during early course lectures; therefore, the course has no prerequisites, and is open to anyone with basic programming knowledge. Students who enrol in this course will master data science fundamentals and directly apply these skills to solve real world challenging business problems.*Terms & Conditions of Exam Guarantee:Ligency Ventures Pty Ltd, U.K provides the following guarantee for the TensorFlow Developer Professional Certificate Course:If you take your TensorFlow Developer Certificate exam within 30 days of enrolling and completing this course 100% and you sit the exam and receive a score above zero, but below the minimum score required to pass the exam, then Ligency Ventures Pty Ltd, U.K will pay for your second exam attempt provided the following conditions are met: you paid at least $1 for this course and it was not refunded, AND before sitting the exam, you diligently watched and followed along with all of the tutorials in the course (completed all case studies and have all codes under your Google Colab account), AND you completed all practical activities including but not limited to challenges within the sections, quizzes, homework exercises and all provided practice exams.Ligency Ventures Pty Ltd may request evidence of fulfilling the above conditions, thereby it's important that you save your work when taking the course and doing the practical assignments.
Overview
Section 1: Part 0: Introduction To The Course
Lecture 1 Introduction to the Course
Lecture 2 Contact and Questions
Section 2: Part 1: Artificial Neural Networks
Lecture 3 Intro
Lecture 4 Get course materials
Lecture 5 Plan of Attack
Lecture 6 Functioning of the Human Neuron
Lecture 7 How Neural Networks Work?
Lecture 8 Activation Function
Lecture 9 How Neural Networks Learn?
Lecture 10 Gradient Descent
Lecture 11 Stochastic Gradient Descent
Lecture 12 Back-Propagation
Lecture 13 Build an ANN with TensorFlow in 5 Steps From Scratch - Step 1
Lecture 14 Build an ANN with TensorFlow in 5 Steps From Scratch - Step 2
Lecture 15 Build an ANN with TensorFlow in 5 Steps From Scratch - Step 3
Lecture 16 Build an ANN with TensorFlow in 5 Steps From Scratch - Step 4
Lecture 17 Build an ANN with TensorFlow in 5 Steps From Scratch - Step 5
Section 3: Part 2: Convolutional Neural Networks
Lecture 18 Intro
Lecture 19 Plan of Attack
Lecture 20 What are Convolutional Neural Networks
Lecture 21 Step 1: The Convolution Operation
Lecture 22 Step 1 (Part B): ReLU Layer
Lecture 23 Step 2: Pooling
Lecture 24 Step 3: Flattening
Lecture 25 Step 4: Full Connection
Lecture 26 Summary
Lecture 27 Softmax Activation Function & Cross-Entropy Loss Function
Lecture 28 Build a CNN with TensorFlow in 5 Steps From Scratch - Step 1
Lecture 29 Build a CNN with TensorFlow in 5 Steps From Scratch - Step 2
Lecture 30 Build a CNN with TensorFlow in 5 Steps From Scratch - Step 3
Lecture 31 Build a CNN with TensorFlow in 5 Steps From Scratch - Step 4
Lecture 32 Build a CNN with TensorFlow in 5 Steps From Scratch - Step 5
Lecture 33 Demo
Section 4: Part 3: Recurrent Neural Networks
Lecture 34 Intro
Lecture 35 Plan of Attack
Lecture 36 Recurrent Neural Networks
Lecture 37 Vanishing Gradient Problem
Lecture 38 LSTMs and How They Work
Lecture 39 Practical Intuition
Lecture 40 LSTM Variations
Lecture 41 Build a RNN with TensorFlow in 15 steps from scratch - Step 1
Lecture 42 Build a RNN with TensorFlow in 15 steps from scratch - Step 2
Lecture 43 Build a RNN with TensorFlow in 15 steps from scratch - Step 3
Lecture 44 Build a RNN with TensorFlow in 15 steps from scratch - Step 4
Lecture 45 Build a RNN with TensorFlow in 15 steps from scratch - Step 5
Lecture 46 Build a RNN with TensorFlow in 15 steps from scratch - Step 6
Lecture 47 Build a RNN with TensorFlow in 15 steps from scratch - Step 7
Lecture 48 Build a RNN with TensorFlow in 15 steps from scratch - Step 8
Lecture 49 Build a RNN with TensorFlow in 15 steps from scratch - Step 9
Lecture 50 Build a RNN with TensorFlow in 15 steps from scratch - Step 10
Lecture 51 Build a RNN with TensorFlow in 15 steps from scratch - Step 11
Lecture 52 Build a RNN with TensorFlow in 15 steps from scratch - Step 12
Lecture 53 Build a RNN with TensorFlow in 15 steps from scratch - Step 13
Lecture 54 Build a RNN with TensorFlow in 15 steps from scratch - Step 14
Lecture 55 Build a RNN with TensorFlow in 15 steps from scratch - Step 15
Section 5: Part 4: Intro to Computer Vision
Lecture 56 Intro
Lecture 57 Introduction to Computer Vision
Lecture 58 Code to Load Training Data For a Computer Vision Task
Lecture 59 Code a First Computer Vision Neural Network
Lecture 60 How to Use Callbacks to Control The Training
Section 6: Part 5: Mastering Convolutions
Lecture 61 Intro
Lecture 62 Dive deeper into convolutions
Lecture 63 Fashion classifier with more advanced convolutions
Lecture 64 New dataset with same more advanced convolutions and further improvement through
Section 7: Part 6: More Complex Images
Lecture 65 Intro
Lecture 66 ImageGenerator
Lecture 67 ConvNet to use on complex images and how to train it with fit_generator
Section 8: Part 7: More Real-World Images
Lecture 68 Intro
Lecture 69 Build and train the ConvNet for Real-World Images
Lecture 70 Automatic validation to test and improve the accuracy, as well as the impact of
Section 9: Part 8: Image Augmentation
Lecture 71 Intro
Lecture 72 Dive deeper into image augmentation
Lecture 73 Code gain the augmentation technique with ImageDataGenerator
Lecture 74 Add that to the cats vs. dogs dataset
Lecture 75 Do the same on the horses vs. humans dataset
Section 10: Part 9: Transfer Learning
Lecture 76 Intro
Lecture 77 Concept of transfer learning
Lecture 78 Transfer learning from the inception mode and use dropouts to reduce overfitting
Lecture 79 Code our own model by using transferred features
Section 11: Part 10: Multi-Class Classification
Lecture 80 Intro
Lecture 81 Moving from binary to multi-class classification and the Rock Paper Scissors dat
Lecture 82 Train a classifier with Rock Paper Scissors and test that same classifier
Section 12: Part 11: Computer Vision in JavaScript
Lecture 83 Intro
Lecture 84 Create a Convolutional Net with JavaScript
Lecture 85 Visualize the Training Process
Lecture 86 How to use the Sprite Sheet, and then tf.tidy() to Save Memory
Section 13: Part 12: Reusing Existing Models in JavaScript
Lecture 87 Intro
Lecture 88 Pre-trained TensorFlow.js models and toxicity Classifier, including in code
Lecture 89 MobileNet using TensorFlow.js and MobileNet Example In Code
Lecture 90 How to convert Models to JavaScript
Section 14: Part 13: Transfer Learning in JavaScript
Lecture 91 Intro
Lecture 92 How to retrain the MobileNet Model using Transfer Learning
Lecture 93 How to capture the Data to train again the network
Lecture 94 How to performing Inference
Section 15: Part 14: Introduction to NLP - Tokenization and Sequences
Lecture 95 Intro
Lecture 96 Introduction to NLP and how word based encodings work
Lecture 97 How to go from text to sequence using the tokenizer
Lecture 98 How padding works, still in the process of preprocessing texts
Section 16: Part 15: Introduction to NLP - Embeddings
Lecture 99 Intro
Lecture 100 Introduction to Embeddings
Lecture 101 IMDB dataset to look into the details of embeddings
Lecture 102 Build a classifier for the sarcasm dataset
Section 17: Part 16: Introduction to NLP - Exploring Recurrent Models
Lecture 103 Intro
Lecture 104 Recurrent Models used for NLP, application and implementation of LSTMs to NLP
Lecture 105 Try using a convolutional neural network for NLP
Section 18: Part 17: Create Text With RNNs
Lecture 106 Intro
Lecture 107 Text generation with RNNs
Lecture 108 Train RNNs on some text data to find what the next word should be in a sequence
Lecture 109 Try to do poetry by using RNNs
Section 19: Part 18: Sequences and Prediction
Lecture 110 Intro
Lecture 111 Understanding of time series, and how to split them into the train, validation a
Lecture 112 Different metrics for evaluating performance of time series, concepts of moving
Section 20: Part 19: Predicting Sequences With Machine Learning
Lecture 113 Intro
Lecture 114 How ML is applied to time series and preparation the features and labels
Lecture 115 How to feed a windowed dataset into a neural network, as well as application and
Lecture 116 Training a deep neural network, tuning it, and making prediction
Section 21: Part 20: Using RNNs With Sequences
Lecture 117 Intro
Lecture 118 How RNNs are used with sequences and what must be the shape of the inputs
Lecture 119 Output a sequence, Lambda layers to improve the performance and the learning rat
Lecture 120 How to use the LSTM with the same sequences
Section 22: Part 21: Real-World Time Series
Lecture 121 Intro
Lecture 122 Use of convolutions for real-world time series and Bi-directional LSTMs for real
Lecture 123 Work on real data about sunspots and train and tune the model
Lecture 124 Will make predictions
Section 23: Real TensorFlow Certification Exam 1
Lecture 125 Lesson 1
Lecture 126 Lesson 2
Lecture 127 Lesson 3
Lecture 128 Lesson 4
Lecture 129 Lesson 5
Section 24: Real TensorFlow Certification Exam 2
Lecture 130 Lesson 1
Lecture 131 Lesson 2
Lecture 132 Lesson 3
Lecture 133 Lesson 4
Lecture 134 Lesson 5
Section 25: Real TensorFlow Certification Exam 3
Lecture 135 Lesson 1
Lecture 136 Lesson 2
Lecture 137 Lesson 3
Lecture 138 Lesson 4
Lecture 139 Lesson 5
Section 26: Course Extra: Introduction to TensorFlow Lite
Lecture 140 Quick Update
Lecture 141 Intro
Lecture 142 TensorFlow Lite features and components (incl. architecture and performance), op
Lecture 143 How to save, convert, and optimize a model, as well as introduction to TF-Select
Lecture 144 How to convert a model to TFLite and how to do Transfer Learning with TFLite
Section 27: Course Extra: TF Lite and Android
Lecture 145 Intro
Lecture 146 Introduction to TF Lite with Android and architecture of a model in Android
Lecture 147 How to initialize the Interpreter
Lecture 148 How to prepare the Input and how to do inference and get results
Section 28: Course Extra: TF Lite and iOS
Lecture 149 Intro
Lecture 150 Introduction to TF Lite with iOS, Swift and TF Lite Swift
Lecture 151 Initializing the interpreter, preparing the inputs, doing inference and getting
Section 29: Course Extra: TF Lite and Micro Systems
Lecture 152 Intro
Lecture 153 Introduction to TF Lite with Micro Systems
Lecture 154 How to start working on a Raspberry Pi and illustrate this with Image classifica
Lecture 155 Initializing the interpreter, preparing the inputs, doing inference and getting
Data Scientists who simply want to learn how to use TensorFlow at an advanced level.,Data Scientists who want to pass the TensorFlow Developer Certification.,AI Practitioners who want to build more powerful AI models using TensorFlow.,Tech enthusiasts who are passionate about AI and want to gain real-world practical experience with TensorFlow.
