Last updated 8/2017MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 859.90 MB | Duration: 4h 36m

Become an expert in machine learning and deep learning with the new TensorFlow 1.x

What you’ll learn

Learn about machine learning landscapes along with the historical development and progress of deep learning

Load, interact, process, and save complex datasets

Solve classification and regression problems using state-of-the-art techniques

Train machines quickly to learn from data by exploring reinforcement learning techniques

Classify images using deep neural network schemes

Learn about deep machine intelligence and GPU computing

Explore active areas of deep learning research and applications

Requirements

Knowledge of Python is a must

Basic knowledge of Math and Statistics would be beneficial, however is not mandatory

Description

Are you a data analyst, data scientist, or a researcher looking for a guide that will help you increase the speed and efficiency of your machine learning activities? If yes, then this course is for you!

Google’s brainchild TensorFlow, in its first year, has more than 6000 open source repositories online. It has helped eeers, researchers, and many others make significant progress with everything from voice/sound recognition to language translation and face recognition. It has also proved to be useful in the early detection of skin cancer and preventing blindness in diabetics. TensorFlow is designed to make distributed machine and deep learning easy for everyone, but using it requires understanding some general principles and algorithms. Furthermore, the latest release of TensorFlow comes with lots of exciting features. It’s incredibly fast, flexible, and more production-ready than ever!

The aim of this course is to help you tackle common commercial machine learning and deep learning problems that you’re facing in your day-to-day activities.

What is included?

Let’s take a look at the learning journey. The course bs with an introduction to machine learning and deep learning. You will explore the main features and capabilities of TensorFlow such as a computation graph, data model, programming model, and TensorBoard. The key highlight here is that this course will teach you how to upgrade your code from TensorFlow 0.x to TensorFlow 1.x. Next, you will learn the different techniques of machine learning such as clustering, linear regression, and logistic regression with the help of real-world projects and examples. You will also learn the concepts of reinforcement learning, the Q-learning algorithm, and the OpenAI Gym framework. Moving ahead, you will dive into neural networks and see how convolution, recurrent, and deep neural networks work and the main operation types used in building them. Next, you will learn advanced concepts such as GPU computing and muldia programming. Finally, the course will demonstrate an example on deep learning on Android using TensorFlow.

By the end of this course, you will have a solid knowledge of the all-new TensorFlow and be able to implement it efficiently in production.

For this course, we have combined the best works of these extremely esteemed authors

Rodolfo Bonnin is a systems eeer and PhD student at Universidad Tecnologica Nacional, Argentina. He also pursued parallel programming and image understanding postgraduate courses at Uni Stuttgart, Germany.He has done research on high performance computing since 2005 and began studying and implementing convolutional neural networks in 2008, writing a CPU and GPU supporting neural network feed-forward stage. More recently, he’s been working in the field of fraud pattern detection with neural networks, and is currently working on signal classification using ML techniques.

He is also the author of the book Building Machine Learning Projects with TensorFlow, Packt Publishing.

Giancarlo Zaccone has more than ten years of experience in managing research projects both in scientific and industrial areas. He worked as a researcher at the National Research Council, where he was involved in projects relating to parallel computing and scientific visualization.

Currently, he is a system and software eeer at a consulting company developing and maintaining software systems for space and defense applications.

He is author of the following Packt books: Python Parallel Programming Cookbook and Getting Started with TensorFlow.

Md. Rezaul Karim has more than 8 years of experience in the area of research and development with a solid knowledge of algorithms and data structures in C/C, Java, Scala, R, and Python, focusing on Big Data technologies such as Spark, Kafka, DC/OS, Docker, Mesos, Zeppelin, Hadoop, and MapReduce, and deep learning technologies such as TensorFlow, DeepLearning4j, and H2O-Sparking Water. His research interests include machine learning, deep learning, semantic web/linked data, Big Data, and bioinformatics.

Ahmed Menshawy is a research eeer at the Trinity College, Dublin, Ireland. He has more than 5 years of working experience in the area of machine learning and natural language processing (NLP). He holds an MSc in Advanced Computer Science. He started his career as a teaching assistant at the Department of Computer Science, Helwan University, Cairo, Egypt.

Overview

Section 1: Getting Started with Machine Learning and Deep Learning

Lecture 1 Course Introduction

Lecture 2 A quick overview

Section 2: First Look at TensorFlow

Lecture 3 Up and running with TensorFlow

Section 3: Exploring and Transfog Data

Lecture 4 TensorFlow’s main data structure – tensors

Lecture 5 Handling the computing workflow – TensorFlow’s data flow graph

Lecture 6 Basic tensor methods

Lecture 7 How TensorBoard works?

Lecture 8 Reading information from a disk

Section 4: Clustering

Lecture 9 Learning from data – unsupervised learning

Lecture 10 Understanding clustering

Lecture 11 Mechanics of k-means

Lecture 12 k-nearest neighbor

Lecture 13 Project 1 – k-means clustering on synthetic datasets

Lecture 14 Project 2 – nearest neighbor on synthetic datasets

Section 5: Linear Regression

Lecture 15 Univariate linear modeling function

Lecture 16 Optimizer methods in TensorFlow – the train module

Lecture 17 Univariate linear regression

Lecture 18 Multivariate linear regression

Section 6: Logistic Regression

Lecture 19 Logistic function predecessor – the logit functions

Lecture 20 The logistic function

Lecture 21 Univariate logistic regression

Lecture 22 Univariate logistic regression with Keras

Section 7: Reinforcement Learning

Lecture 23 Dive into reinforcement learning

Section 8: Simple Feed-Forward Neural Networks

Lecture 24 Preliminary concepts

Lecture 25 First project – nonlinear synthetic function regression

Lecture 26 Second project – modeling cars fuel efficiency with nonlinear regression

Lecture 27 Third project – learning to classify wines (multiclass classification)

Section 9: Convolutional Neural Networks

Lecture 28 Origin of convolutional neural networks

Lecture 29 Applying convolution in TensorFlow

Lecture 30 Subsampling operation – pooling

Lecture 31 Improving efficiency – dropout operation

Lecture 32 Convolutional type layer building methods

Lecture 33 MNIST digit classification

Lecture 34 Image classification with the CIFAR10 dataset

Section 10: Autoencoders

Lecture 35 Optimizing TensorFlow autoencoders

Section 11: Recurrent Neural Networks

Lecture 36 Recurrent neural networks

Lecture 37 A fundamental component – gate operation and its steps

Lecture 38 TensorFlow LSTM useful classes and methods

Lecture 39 Univariate series prediction with energy consumption data

Lecture 40 Writing music “a la” bach

Section 12: Deep Neural Networks

Lecture 41 Deep neural network definition and architectures through

Lecture 42 Alexnet

Lecture 43 Inception V3

Lecture 44 Residual Networks (ResNet)

Lecture 45 Painting with style – VGG style transfer

Section 13: GPU Computing

Lecture 46 Getting started with GPU computing

Section 14: Advanced TensorFlow Programming

Lecture 47 TensorFlow – Keras, Pretty Tensor, TFLearn, and much more!

Section 15: Advanced Muldia Programming with TensorFlow

Lecture 48 Getting started with muldia programming

This 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 course extremely helpful