TensorFlow: Introduction to Machine Learning

Course: 1 Hour, 41 Minutes

• Course Overview
• Introduction to Machine Learning Algorithms
• Understanding Machine Learning
• Understanding Deep Learning
• Supervised and Unsupervised Learning
• TensorFlow for Machine Learning
• Tensors and Operators
• Understanding How to Install TensorFlow
• Installing TensorFlow on the Local Machine
• Working with Constants
• The Computation Graph with TensorBoard
• Working with Variables and Placeholders
• Variables and Placeholders on TensorBoard
• Updating Variables in a Session
• Feed Dictionaries
• Named Scopes for Better Visualization
• Eager Execution
• Exercise: Machine Learning and TensorFlow
• Exercise: Working with Computation Graph

TensorFlow: Simple Regression and Classification Models

Course: 1 Hour, 38 Minutes

• Course Overview
• Understanding Linear Regression
• Gradient Descent and Optimizers
• Explore the Boston Housing Prices Dataset
• Creating Training and Test Datasets for Regression
• Base Model with scikit-learn
• Setting up the Linear Regression Computation Graph
• Train and Visualize the Linear Regression Model
• Visualize the Model with TensorBoard
• The High-Level Estimator API
• Linear Regression with Estimators
• Prediction Using Estimators
• Understanding Binary Classification
• The Cross Entropy Loss Function and Softmax
• Continuous and Categorical Data
• Creating Training & Test Datasets for Classification
• Binary Classification Using Estimators
• Exercise: Working with Linear Regression
• Exercise: Working with Binary Classification

TensorFlow: Deep Neural Networks and Image Classification

Course: 1 Hour, 18 Minutes

• Course Overview
• Neural Networks and Deep Learning
• Basic Structure of a Neural Network
• The Mathematical Function Applied By a Neuron
• Linear Transformation and Activation Functions
• Training a Neural Network Using Gradient Descent
• Forward Pass and Backward Pass
• Image Representations in Machine Learning
• Set Up TensorFlow and Use Jupyter Notebooks
• The MNIST Dataset
• Training an Estimator for Image Classification
• Predicting Image Labels
• Drawbacks of Deep Neural Networks for Images
• Exercise: Working with Neural Networks
• Exercise: Working with Image Classification

TensorFlow: Convolutional Neural Networks for Image Classification

Course: 1 Hour, 21 Minutes

• Course Overview
• Neural Networks and Deep Learning
• Basic Structure of a Neural Network
• The Mathematical Function Applied By a Neuron
• Linear Transformation and Activation Functions
• Training a Neural Network Using Gradient Descent
• Forward Pass and Backward Pass
• Image Representations in Machine Learning
• Set Up TensorFlow and Use Jupyter Notebooks
• The MNIST Dataset
• Training an Estimator for Image Classification
• Predicting Image Labels
• Drawbacks of Deep Neural Networks for Images
• Exercise: Working with Neural Networks
• Exercise: Working with Image Classification
• Explore how to model language and

Tensorflow: Word Embeddings & Recurrent Neural Networks

Course: 40 Minutes

• Course Overview
• One-Hot Encoding of Words
• Frequency-Based Encoding
• Prediction-Based Encoding
• Word2vec and GloVe Embeddings
• Recurrent Neurons
• Unrolling a Recurrent Memory Cell
• Training a Recurrent Neural Network
• Long Memory Cells
• Exercise: Working with Word Encoding
• Exercise: Working with Recurrent Neural Networks

Tensorflow: Sentiment Analysis with Recurrent Neural Networks

• Course: 58 Minutes
   
• Course Overview
• Configuring the TensorFlow Environment
• Training Data
• Data Pre-Processing
• Unique Identifiers to Represent Words
• Construct a Recurrent Neural Network
• Training the Neural Network
• Data Pre-Processing to Use Pre-Trained Word Vectors
• Lookup Table to Map Unique Identifiers
• Sentences Using Word Identifiers
• Sentiment Analysis Using Pre-Trained Vectors
• Exercise: Performing Sentiment Analysis

Tensorflow: K-means Clustering with TensorFlow

Course: 1 Hour

• Course Overview
• Supervised vs. Unsupervised Learning
• Supervised Learning Characteristics
• Unsupervised Learning Characteristics
• Unsupervised Learning Use Cases
• Objectives of Clustering Techniques
• K-means Clustering
• K-means Clustering Algorithm
• Install TensorFlow and Work with Jupyter Notebooks
• Generate Random Data for K-means Clustering
• K-means Clustering Using Estimators
• The Iris Dataset
• Clustering the Iris Dataset
• Exercise: Working with Unsupervised Learning
• Exercise: Working with Clustering

Tensorflow: Building Autoencoders in TensorFlow

Course: 47 Minutes

• Course Overview
• Efficient Representation of Data Using Encodings
• Autoencoders
• Principal Component Analysis
• Performing Principal Component Analysis on Datasets
• Principal Component Analysis with scikit-learn
• Autoencoders for Principal Component Analysis
• The Fashion MNIST Dataset
• Autoencoders for Dimensionality Reduction
• Exercise: Working with Autoencoders

Tensorflow: Word Embeddings & Recurrent Neural Networks

Course: 44 Minutes

• Course Overview
• One-Hot Encoding of Words
• Frequency-Based Encoding
• Prediction-Based Encoding
• Word2vec and GloVe Embeddings
• Recurrent Neurons
• Unrolling a Recurrent Memory Cell
• Training a Recurrent Neural Network
• Long Memory Cells3
• Exercise: Working with Word Encoding
• Exercise: Working with Recurrent Neural Networks

TensorFlow: Convolutional Neural Networks for Image Classification

Course: 1 Hour, 23 Minutes

• Course Overview
• The Visual Cortex
• Convolution and Convolutional Layers
• Image as an Input Matrix
• Convolution Kernel and Convolutional Layer
• Edge Detection Using Convolution
• Pooling and Pooling Layers
• Zero-Padding and Stride Size
• Convolutional Neural Network Architecture
• Overfitting and the Bias-Variance Trade-Off
• Preventing Overfitting
• The CIFAR-10 Dataset
• Training and Test Dataset for Image Classification
• Placeholders and Variables for the CNN
• CNN for Image Classification
• Train and Predict Using a CNN
• Exercise: Working with CNNs

TensorFlow: Deep Neural Networks and Image Classification

Course: 1 Hour, 18 Minutes

• Course Overview
• Neural Networks and Deep Learning
• Basic Structure of a Neural Network
• The Mathematical Function Applied By a Neuron
• Linear Transformation and Activation Functions
• Training a Neural Network Using Gradient Descent
• Forward Pass and Backward Pass
• Image Representations in Machine Learning
• Set Up TensorFlow and Use Jupyter Notebooks
• The MNIST Dataset
• Training an Estimator for Image Classification
• Predicting Image Labels
• Drawbacks of Deep Neural Networks for Images
• Exercise: Working with Neural Networks
• Exercise: Working with Image Classification