Course Description

Engaging projects that will teach you how complex data can be exploited to gain the most insight

About This Video

• Bored with too much theory on TensorFlow? This book is what you need! Thirteen solid projects and four examples teach you how to implement TensorFlow in production.
• This example-rich guide teaches you how to perform highly accurate and efficient numerical computing with TensorFlow.
• A practical and methodically explained guide that allows you to apply Tensorflow's features from scratch.

In Detail

This video, with the help of practical projects, highlights how TensorFlow can be used in different scenarios—this includes projects for training models, machine learning, deep learning, and working with various neural networks. Each project provides exciting and insightful exercises that will teach you how to use TensorFlow and show you how layers of data can be explored by working with tensors. Simply pick a project in line with your environment and get stacks of information on how to implement TensorFlow in production.

This course is for professionals within the following business functions:

• This video course is for data analysts, data scientists, and researchers who want to increase the speed and efficiency of their machine learning activities and results. Anyone looking for a fresh guide to complex numerical computations with TensorFlow will find this an extremely helpful resource. This video is also for developers who want to implement TensorFlow in production in various scenarios.

1. Exploring and Transforming Data - 38 Minutes

   1. The Course Overview
   2. TensorFlow's Main Data Structure – Tensors
   3. Handling the Computing Workflow – TensorFlow's Data Flow Graph
   4. Basic Tensor Methods
   5. How TensorBoard Works?
   6. Reading Information from Disk

2. Clustering - 18 Minutes

   1. Learning from Data –Unsupervised Learning
   2. Mechanics of k-Means
   3. k-Nearest Neighbor
   4. Project 1 – k-Means Clustering on Synthetic Datasets
   5. Project 2 – Nearest Neighbor on Synthetic Datasets

3. Linear Regression - 19 Minutes

   1. Univariate Linear Modelling Function
   2. Optimizer Methods in TensorFlow – The Train Module
   3. Univariate Linear Regression
   4. Multivariate Linear Regression

4. Logistic Regression - 20 Minutes

   1. Logistic Function Predecessor – The Logit Functions
   2. The Logistic Function
   3. Univariate Logistic Regression
   4. Univariate Logistic Regression with keras

5. Simple FeedForward Neural Networks - 16 Minutes

   1. Preliminary Concepts
   2. First Project – Non-Linear Synthetic Function Regression
   3. Second Project – Modeling Cars Fuel Efficiency with Non-Linear Regression
   4. Third Project – Learning to Classify Wines: Multiclass Classification

6. Convolutional Neural Networks - 20 Minutes

   1. Origin of Convolutional Neural Networks
   2. Applying Convolution in TensorFlow
   3. Subsampling Operation –Pooling
   4. Improving Efficiency – Dropout Operation
   5. Convolutional Type Layer Building Methods
   6. MNIST Digit Classification
   7. Image Classification with the CIFAR10 Dataset

7. Recurrent Neural Networks and LSTM - 21 Minutes

   1. Recurrent Neural Networks
   2. A Fundamental Component – Gate Operation and Its Steps
   3. TensorFlow LSTM Useful Classes and Methods
   4. Univariate Time Series Prediction with Energy Consumption Data
   5. Writing Music "a la" Bach

8. Deep Neural Networks - 13 Minutes

   1. Deep Neural Network Definition and Architectures Through Time
   2. Alexnet
   3. Inception V3
   4. Residual Networks (ResNet)
   5. Painting with Style – VGG Style Transfer

9. Library Installation and Additional Tips - 6 Minutes

   1. Windows Installation
   2. macOS Installation