by Salil Vishnu Kapur | Released July 2018 | ISBN: 9781789344752

Build smart systems with ease using TensorFlowAbout This VideoAn easy and fast way to explore deep learning models while using the highly popular TensorFlow libraryBlend of theory and practical implementation with complete Jupyter notebook code guides, along with easy-to-reference practical examplesGain proficiency in building deep learning projects using TensorFlow without any need to delve into writing models from scratchIn DetailAre you short on time to start from scratch to use deep learning to solve complex problems involving topics like neural networks and reinforcement learning? If yes, then this is the course to help you. This course is designed to help you to overcome various data science problems by using efficient deep learning models built in TensorFlow.The course begins with a quick introduction to TensorFlow essentials. Next, we start with deep neural networks for different problems and then explore the applications of Convolutional Neural Networks on two real datasets. If you're facing time series problem then we will show you how to tackle it using RNN. We will also highlight how autoencoders can be used for efficient data representation. Lastly, we will take you through some of the important techniques to implement generative adversarial networks. All these modules are developed with step by step TensorFlow implementation with the help of real examples.By the end of the course you will be able to develop deep learning based solutions to any kind of problem you have, without any need to learn deep learning models from scratch, rather using tensorflow and it's enormous power. Show and hide more Publisher Resources Download Example Code

1. Chapter 1 : Setting Up the Deep Learning Playground
   • The Course Overview 00:04:26
   • TensorFlow for Building Deep Learning Models 00:04:22
   • Basic Syntaxes, Function Optimization, Variables, and Placeholders 00:07:17
   • TensorBoard for Visualization 00:04:12
2. Chapter 2 : Training Deep Feed-forward Neural Networks with TensorFlow
   • Start by Loading the Imported Dataset 00:03:49
   • Building the Layers of the Neural Network in TensorFlow 00:06:14
   • Optimizing the Softmax Cross Entropy Function 00:03:23
   • Using DNN Predicting Whether Breast Cancer Cells Are Benign or Not 00:05:08
3. Chapter 3 : Applying CNN on Two Real Datasets
   • Importing the Two Datasets Using TensorFlow and Sklearn API 00:04:23
   • Writing the TensorFlow Code to Add Convolutional and Pooling Layers 00:11:22
   • Using tf.train.AdamOptimizer API to Optimize CNN 00:03:44
   • Implementing CNN to Create a Face Recognition System 00:03:59
4. Chapter 4 : Exercise RNN to Solve Two Time Series Problems
   • Understanding the RNN and the Need for LSTM 00:02:24
   • Implementing RNN 00:03:11
   • Monthly Riverflow Prediction of Turtle River in Ontario 00:08:48
   • Implement LSTM Project to Predict Decimal Number of Given Binary Representation 00:12:10
5. Chapter 5 : Using Autoencoders to Efficiently Represent Data
   • Encoder and Decoder for Efficient Data Representation 00:03:32
   • TensorFlow Code Using Linear Autoencoder to Perform PCA on a 4D Dataset 00:04:49
   • Using Stacked Autoencoders for Representation on MNIST Dataset 00:06:29
   • Build a Deep Autoencoder to Reduce Latent Space of LFW Face Dataset 00:05:06
6. Chapter 6 : Generative Adversarial Networks for Creating Synthetic Dataset
   • Generator and Discriminator the Basics of GAN 00:03:16
   • Downloading and Setting Up the (Microsoft Research Asia) Geolife Project Dataset 00:04:51
   • Coding the Generator and Discriminator Using TensorFlow 00:04:02
   • Training GANs to Create Synthetic GPS Based Trajectories 00:10:06
Show and hide more