Last updated 1/2019MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 3.22 GB | Duration: 8h 15m

Practical recipes on Neural Network modeling, Reinforcement & Transfer Learning using Python's Deep Learning tools

What you'll learn

Build a Deep Learning-based image recognition system using Python and learn how to deploy and integrate it into web apps or phone apps.

Identify mean tweets, detect smiles in your camera app, forecast stock prices, and more using Neural Networks.

Select the best Python framework for Deep Learning such as PyTorch, Tensorflow, MXNet, and Keras.

Reuse Python code snippets and adapt them to everyday problems.

Implement some state-of-the-art computer vision algorithms using deep learning and Python.

Evaluate the cost/benefits and performance implication of each discussed solution.

Requirements

Python programming knowledge is essential. A thorough understanding of Machine Learning concepts and Python libraries such as NumPy, SciPy, and scikit-learn is expected.

Description

Deep Learning is revolutionizing a wide range of industries. Deep Learning allows you to solve problems where traditional Machine Learning methods might perform poorly: detecting and extracting objects from images, extracting meaning from text, and predicting outcomes based on complex dependencies, to name a few. If you're a Data Scientist who have basic Machine Learning knowledge and want to explore the possibilities of Deep Learning, then this Course is perfect for you!This comprehensive 3-in-1 course is a direct, practical, and very hands-on approach where we deal less with theory and adopt a more hands-on style of learning. Initially, you’ll get hands-on experience building basic neural network models (and no maths!) using Python. You’ll also build a deep learning-based image recognition system using Python and learn how to deploy and integrate it into web apps or phone apps. Moving further, a discussion on the corresponding pros and cons of implementing solutions using a popular framework such as TensorFlow, PyTorch, and Keras is provided. Finally, you’ll reuse Python code snippets and adapt them to everyday problems also, evaluate the cost/benefits and performance implication of each solution.By the end of this course, you'll apply Deep Learning concepts and use Python to solve challeg tasks. Identify mean tweets, detect smiles in your camera app, forecast stock prices, and more using Neural Networks.Contents and OverviewThis training program includes 3 complete courses, carefully chosen to give you the most comprehensive training possible.The first course, Python Deep Learning for Bners, covers applying Deep Learning concepts and use Python to solve challeg tasks. This course will teach you to apply deep learning concepts using Python to solve challeg tasks. You'll build a Python deep learning-based image recognition system and deploy and integrate images into web apps or phone apps. You will start out with an intuitive understanding of neural networks in general. We will guide you through the building blocks of deep learning networks to tackle complex neural networks. So, take this course and learn the skills and temperament need to enter the AI marketplace today.The second course, Real-World Python Deep Learning Projects, covers identifying mean tweets, detect smiles in your camera app, forecast stock prices, and more using Neural Networks. You will start off by creating neural networks to predict the demand for airline travel in the future. Then, you'll run through a scenario where you have to identify negative tweets for a celebrity by using Convolutional Neural Networks (CNN's). Next, you will create a neural network which will be able to identify smiles in your camera app. Finally, the last project will help you forecast a company's stock prices for the next day using Deep Learning. By the end of this course, you will have a solid understanding of Deep Learning and the ability to build your own Deep Learning models.The third course, Python Deep Learning Solutions, covers over 20 practical videos on neural network modeling, reinforcement learning, and transfer learning using Python. The course includes solutions that are related to the basic concepts of neural networks; all techniques, as well as classical network topologies, are covered. The main purpose of this video course is to provide Python programmers with a detailed list of solutions so they can apply Deep Learning to common and not-so-common scenarios.By the end of this course, you'll apply Deep Learning concepts and use Python to solve challeg tasks. Identify mean tweets, detect smiles in your camera app, forecast stock prices, and more using Neural Networks.About the AuthorsDes Drury is a passionate technologist with many years' experience in all aspects of data center infrastructure, automation, programming languages, and developer workflows. He is: - Co-organizer of the Melbourne Kubernetes Meetup - Author of Open Datacentre, a Kubernetes distribution with numerous datacenter workloads; - A Kubernetes evangelist from the early days of its release; - Passionate about helping teams to understand complex technology - Teaches the skills required for team members to solve their own problems - An excellent communicator and enjoys helping people, passing on knowledge, and improving processes He has also built numerous tools that have been adopted as enterprise solutions and has received a number of awards.Braithe E.S. Warnock is currently a Managing Cloud Architect for the Financial Services division of Ernst & Young. He has had the opportunity to work with several of the largest PCF installations on an international scale. He helped build the framework for the adoption of PCF at top companies such as Ford, Comcast, DISH, HSBC, and Charles Schwab. As a vendor-neutral consultant, Braithe enjoys helping people understand the rapidly-evolving world of cloud and application architectures. Braithe has more than six years' experience and specialization in global digital transformations. He has expertise in various cloud and cloud platform technologies (PCF, AWS, Azure, VMware, Netflix OSS, Kubernetes, and OpenShift) and also the Java and Spring Boot frameworks. He has developed over 100 microservices using Spring Boot, Java 7/8, Spring Cloud, and Netflix OSS, spanning half a dozen unique cloud-native microservice architectures. He also has experience in developing machine learning models using AWS, Spark, and MLlib to support product recommendations and enhance customer data.Jan Stomphorst is a senior solution architect with more than 20 years' experience in the automation industry; he creates the best solutions for his customers. He uses advanced technical solutions to help developers create stable continuous pipelines and develop systems for 100% up. He is a Docker and Kubernetes expert. He supports several customers with on-premise and in-the-cloud Kubernetes strats.

Overview

Section 1: Python Deep Learning for Bners

Lecture 1 The Course Overview

Lecture 2 A Brief History of Deep Learning

Lecture 3 Deep Learning Today

Lecture 4 Tools, Requirements, and Setup

Lecture 5 Exploring Supervised Learning

Lecture 6 Representational Learning and Feature Eeering

Lecture 7 Linear Regression

Lecture 8 The Perceptron

Lecture 9 Feedforward Networks

Lecture 10 Backpropagation

Lecture 11 Neural Networks from Scratch

Lecture 12 Overfitting and Regularization

Lecture 13 Understanding CNNs

Lecture 14 Implementing a CNN

Lecture 15 Deep CNNs

Lecture 16 Very Deep CNNs

Lecture 17 Batch Normalization

Lecture 18 Fine-Tuning

Lecture 19 Semantic Sntation

Lecture 20 Fully Convolutional Networks

Lecture 21 Recurrent Neural Networks

Lecture 22 LSTM and Advancements

Lecture 23 Building a CNN to Detect General Images

Lecture 24 Training and Deploying on a Cluster

Lecture 25 Comparison of DL Frameworks

Lecture 26 Exciting Areas for Upcoming Research

Section 2: Real-World Python Deep Learning Projects

Lecture 27 The Course Overview

Lecture 28 What Types of Problems Can You Solve Using Deep Learning?

Lecture 29 Installing Essential DL Tools

Lecture 30 Based on Past Data, Predicting the Number of Airline Passengers

Lecture 31 Getting and Preparing Airline Data

Lecture 32 Building Your Multilayer Perceptron Model

Lecture 33 Training and Testing Your Model

Lecture 34 Making Predictions and What's Next?

Lecture 35 End Goal – Label a Given Tweet (Short Text) as Negative or Positive

Lecture 36 Dataset Overview

Lecture 37 Preparing Data for Sennt Analysis

Lecture 38 What Are Word Embeddings and Why They Are Important When Working with CNNs?

Lecture 39 Building Your CNN Model for Text Classification

Lecture 40 Training and Testing Your Model

Lecture 41 Detecting Mean Tweets Using Your Model and What’s Next?

Lecture 42 Detect Whether an Image Contains a Smile with High Accuracy

Lecture 43 Getting and Preparing Data for Smile Detection

Lecture 44 Building Your CNN Model for Smile Detection.

Lecture 45 Training and Testing Your Model

Lecture 46 Detecting Smiles with Your Model and What’s Next?

Lecture 47 Predict the Closing Stock Price of a Given Company for the Next Day

Lecture 48 Getting and Preparing Stock Prices Data

Lecture 49 Building Your LSTM Model for Price Prediction

Lecture 50 Training and Testing Your Model

Lecture 51 Detecting Closing Stock Price with Your Model and What’s Next?

Section 3: Python Deep Learning Solutions

Lecture 52 The course overview

Lecture 53 Understanding TensorFlow, Keras and PyTorch Framework

Lecture 54 Deep Learning Using CNTK and Gluon Framework

Lecture 55 Implementing Single and Multi-Layer Neural Network

Lecture 56 Expent with Activation Functions, Hidden Layers, and Hidden Units

Lecture 57 Autoencoder, Loss Function, and Optimizers

Lecture 58 Overfitting Prevention Methods

Lecture 59 Optimization Techniques for CNNs

Lecture 60 Expenting with Different Types of Initialization

Lecture 61 Implementing Simple RNN and LSTM

Lecture 62 Implementing GRUs and Bidirectional RNNs

Lecture 63 Implementing Generative Adversarial Networks

Lecture 64 Computer Vision Techniques

Lecture 65 Detecting Facial Key Points and Transferring Styles

Lecture 66 Hyper Parameter Selection and Tuning

Lecture 67 Speech Recognition

Lecture 68 Series and Structured Data

Lecture 69 Visualizing and Analysing Network

Lecture 70 Freezing and Storing the Network

Lecture 71 Using InceptionV3 and ResNet50 Model

Lecture 72 Leveraging VGG Model and Fine Tuning

Developers, Analysts, and Data Scientists who have basic Machine Learning knowledge and want to explore the possibilities of Deep Learning as well as use Deep Learning algorithms to create real-world applications using Python.

HomePage:

gfxtra__Deep_Learn.part1.rar.html

gfxtra__Deep_Learn.part2.rar.html

gfxtra__Deep_Learn.part3.rar.html

gfxtra__Deep_Learn.part4.rar.html