PAC | Deep Learning And Neural Networks Using Python. Keras: The Complete Beginners Guide (2019 EN)

Discussion in 'Artificial Intelligence' started by Kanka, Jul 17, 2019.

  1. Kanka

    Kanka Well-Known Member Loyal User

    Likes Received:
    Trophy Points:

    Company: Packt Publishing
    Author: Abilash Nelson
    Full Title: Deep Learning And Neural Networks Using Python - Keras: The Complete Beginners Guide
    Year: 2019
    Language: English
    Genre: Educational: Big data
    Skill Level: Beginner
    Price: €18.19
    Files: MP4
    Time: 11:06:27
    Video: AVC, 1920 x 1080 (1.778) at 30.000 fps, 600 kbps
    Audio: AAC at 126 Kbps, 2 channels, 44.1 KHz

    Deep learning and data science using a Python and Keras library - The complete guide from beginner to professional.

    The world has been obsessed with the terms "machine learning" and "deep learning" recently. We use these technologies every day, with or without our knowledge. Ranging from Google suggestions, to translations, ads, movie recommendations, friend suggestions, sales and customer experiences. There are tons of other applications too so there’s no wonder that deep learning and machine learning specialists, along with data science practitioners, are the most sought-after talent in the current technology world. But the problem is that, when you think about learning these technologies, there is a common misconception that it’s a prerequisite to study lots of maths, statistics, and complex algorithms. It’s almost like someone making you believe that you must learn the working of an internal combustion engine before you learn how to drive a car. The fact is that, to drive a car, we just only need to know how to use the user-friendly control pedals extending from the engine like the clutch, brake, accelerator, steering wheel, and so on. And with a bit of experience, you can easily drive a car. The basic know-how about the internal working of the engine is of course an added advantage while driving a car, but it’s not mandatory.

    Similarly, in our deep learning course, we have a perfect balance between learning the basic concepts and the implementation of the built-in deep learning classes and functions from the Keras library using the Python programming language. These classes, functions and APIs are just like the control pedals from the car engine that we can use easily to build an efficient deep-learning model. Let’s see how this course is organized and an overview about the list of topics included. Overall, this is a basic to advanced crash course in deep learning neural networks and convolutional neural networks using Keras and Python. Once completed, it’s sure to sky-rocket your current career prospects as this in-demand skill is the technology of the future. There is a day in the near future itself, when deep learning models will out-perform human intelligence. So be ready and let’s dive into the world of thinking machines.

    Style and Approach:
    Exhaustive and packed with step-by-step instructions, working examples, and helpful advice, this course is divided into clear chunks so you can learn at your own pace and focus on your own area of interest.

    ✓ Deep learning
    ✓ Neural networks using Python

    ✓ Learn data science using a Python and Keras Library
    ✓ Learn convolutional neural networks using Python

    01. Course Intro and Table of Contents
    02. Deep Learning Overview
    03. Chosing ML or DL for your project
    04. Preparing Your Computer
    05. Python Basics
    06. Installing Theano Library and Sample Program to Test
    07. TensorFlow library Installation and Sample Program to Test
    08. Keras Installation and Switching Theano and TensorFlow Backends
    09. Multi-Layer Perceptron Concepts
    10 Training Neural Network - Steps and Terminology
    11. First Neural Network with Keras - Understanding Pima Indian Dataset
    12. Training and Evaluation Concepts Explained
    13. Pima Indian Model - Steps Explained
    14. Pima Indian Model - Performance Evaluation
    15. Understanding Iris Flower Dataset
    16. Developing the Iris Flower Model
    17. Understanding the Sonar Returns Dataset
    18. Developing the Sonar Returns Model
    19. Sonar Model Perfomance Improvement
    20. Understanding the Boston Housing Dataset
    21. Developing the Boston Housing Baseline Model
    22. Boston Performance Improvement
    23. Save the Trained Model as JSON File (Pima Indian Dataset)
    24. Save and Load Model as YAML File - Pima Indian Dataset
    25. Load and Predict using the Pima Indian Model
    26. Save Load and Predict using Iris Flower Dataset
    27. Save Load and Predict using Sonar Dataset
    28. Save Load and Predict using Boston Dataset
    29. Checkpointing Models
    30. Plotting Model Behaviour History
    31. Dropout Regularisation
    32. Learning Rate Schedule using Ionosphere Dataset
    33. Convolutional Neural Networks – Introduction
    34. Downloading the MNIST Handwritten Digit Dataset
    35. Multi-Layer Perceptron Model using MNIST
    36. Convolutional Neural Network Model using MNIST
    37. Convolutional Neural Network Model using MNIST - Part 2
    38. Large CNN using MNIST
    39. Load Save and Predict using MNIST
    40. Introduction to Image Augmentation using Keras
    41. Augmentation using Sample Wise Standardization
    42. Augmentation using Feature Wise Standardization and ZCA Whitening
    43. Augmentation using Rotation and Flipping
    44. Saving Augmentation for MNIST
    45. CIFAR-10 Object Recognition Dataset - Understanding and Loading
    46. Simple CNN using CIFAR-10 Dataset
    47. Simple CNN using CIFAR-10 Dataset - Part 2
    48. Simple CNN using CIFAR-10 Dataset – Coding
    49. Train and Save CIFAR-10 Model
    50. Load and Predict using CIFAR-10 CNN Model

    Last edited: Jul 22, 2019