Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
LEARNING PATH: Keras: Deep Learning with Keras
Rating: 3.9 out of 5(14 ratings)
150 students

LEARNING PATH: Keras: Deep Learning with Keras

Grasp all the knowledge you need to train your own deep learning models to solve different kinds of problems
Created byPackt Publishing
Last updated 3/2018
English

What you'll learn

  • Understand the main concepts of machine learning and deep learning
  • Build, train, and run fully-connected, convolutional and recurrent neural networks
  • Optimize deep neural networks through efficient hyper parameter searches
  • Work with any kind of data involving images, text, time series, sound and videos
  • Use GPUs to leverage the training experience
  • Build your own Multilayer Neural Networks
  • Build Convolutional Neural Networks and Recurrent Neural Networks
  • Build Auto encoders and Generative Adversarial Networks

Course content

2 sections • 72 lectures • 7h 54m total length

  • The Course Overview2:15

    This video provides an overview of the entire course.

  • What is Deep Learning?5:12

    Before going into the concepts of deep learning, it is important we understand what deep learning is.

  • Machine Learning Concepts23:54

    Like all other technologies, Machine Learning also has some basics concepts which are important.

  • Foundations of Neural Networks9:49

    In this video, we will learn essential concepts of fully connected architecture.

  • Optimization11:33

    Optimization of models is very important and this video discusses about it.

  • Configuration of Keras8:15
    To get going with Keras, the first step would be to set up a GPU in an Amazon instance or a computer, and install Keras.
  • Presentation of Keras and Its API19:42
    What is a model in Keras and how do we design, train, evaluate and predict a model?
  • Design and Train Deep Neural Networks13:12

    In this video, as the name suggests, we will go through the designing, training and visualization phase with Keras.

  • Regularization in Deep Learning11:27

    Effective regularization is important for proper functioning of our models with real inputs. This video deals with some regularization techniques.

  • Introduction to Computer Vision7:57

    Computer vision was the first field revolutionized by deep learning.

  • Convolutional Networks8:19
    Convolution networks are very good at image classification.
  • CNN Architectures6:15

    In this video, we will learn about CNN architectures and research trends.

  • Image Classification Example6:44

    In this video, we will implement convolutional networks in Keras.

  • Image Segmentation Example4:42

    This video discusses what segmentation in deep learning is

  • Introduction to Recurrent Networks4:16
    This video introduces recurrent network and sequential data
  • Recurrent Neural Networks6:39

    What makes neural network recurrent?

    • Define recurrent neural network
    • See an example of a recurrent network in Keras
  • “One to Many” Architecture3:33

    What is one to many architecture?

    • Define one to many architecture in Keras
    • Go through an image captioning demonstration
  • “Many to One” Architecture7:33

    What is a many to one architecture?

    • Define many to one architecture in Keras
    • Run a sentiment analysis
  • “Many to Many” Architecture7:52

    What is a many to many architecture?

    • Define many to many architecture in Keras
    • Implement a text generation task in Keras
  • Embedding Layers7:51
    Embedding layer is widely used in deep learning.
  • What are Recommender Systems?4:44

    We get to know what is behind the term recommender system and its applications.

  • Content/Item Based Filtering7:49
    Here we further extend our knowledge of collaborative filtering with a Keras example.
  • Collaborative Filtering12:28
    In this video we go through user based collaborative filtering with a Keras example.
  • Hybrid System6:28

    In this video we will talk about hybrid systems and extend the Keras example from the previous video.

  • Introduction to Neural Style Transfer5:23

    This video is about neural style transfer and how it works. We also cover a brief overview of the optimization phase.

  • Single Style Transfer4:16

    This video is a hands-on demonstration of style transfer.

  • Advanced Techniques7:50
    In this video, we will go through some of the advanced techniques of style transfer.
  • Style Transfer Explained11:03
    This video explains style transfer and its underlying mechanism in depth.
  • Data Augmentation4:59
    In this video, we discuss data augmentation and its main features.
  • Transfer Learning15:55
    In this video, we will discuss transfer learning and its applications.
  • Hyper Parameter Search8:39

    We have used the term hyper parameter search a number of times in the past videos; here we formally introduce the term and how to effectively use it in Keras

  • Natural Language Processing10:28

    This video explains what natural language is processing and what purpose does it solve.

  • An Introduction to Generative Adversarial Networks (GAN)8:53

    This video is an introduction to GAN.

  • Run Our First GAN9:33

    This video demonstrates how to train and run a basic generative adversarial network.

  • Deep Convolutional Generative Adversarial Networks (DCGAN)5:49

    This video explains what a DCGAN is, and why is it so popular.

  • Techniques to Improve GANs9:59

    GANs are still at a research stage and so it is important that we learn empirical techniques to make GANs work better.

  • Test Your Knowledge

Requirements

  • Prior knowledge of Python and Keras is a must.

Description

Keras is a deep learning library written in Python for quick, efficient training of deep learning models, and can also work with Tensorflow and Theano. Because of its lightweight and very easy to use nature, Keras has become popularity in a very short span of time. So, if you are a data scientist with experience in machine learning with some exposure to neural networks, then go for this Learning Path.

Packt’s Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.

The highlights of this Learning Path are:

  • Understand the main concepts of machine learning and deep learning
  • Work with any kind of data involving images, text, time series, sound and videos
  • Learn to build auto encoders and generative adversarial networks

Let’s take a quick look at your learning journey. You will start with the basics of Keras, in a highly practical manner. You will then dive into deep learning with convolutional and recurrent neural networks, which are the cornerstones of deep learning. You will then take to look at recommender system and some of its types. You will move ahead with a popular Keras framework for style transfer, some advanced techniques and in-depth explanations of the style transfer mechanism. You will also learn to build, train and run generative adversarial networks, go through some of its most popular architectures, and learn techniques to make them work better. Next,  you will get an hands-on training of CNNs, RNNs, LSTMs, autoencoders and generative adversarial networks using real-world training datasets. Finally, you will learn the concepts and applications of generative adversarial networks, implementation with Keras, using Batch Normalization to improve performance.

By the end of this Learning Path, you will be well-versed with deep learning and its implementation with Keras and will be able to solve different kinds of problems.

Meet Your Expert:

We have the best works of the following esteemed author to ensure that your learning journey is smooth:

  • Philippe Remy is a research engineer and entrepreneur working on deep learning and living in Tokyo, Japan. As a research engineer, Philippe reads scientific papers and implements artificial intelligence algorithms related to handwriting character recognition, time series analysis, and natural language processing. As an entrepreneur, his vision is to bring a meaningful and transformative impact to society with the ultimate goal of enhancing overall quality of life and pushing the limits of what is considered possible today. Philippe contributes to different open source projects related to deep learning and fintech (github. com/philipperemy). You can visit Philippe Remy’s blog on philipperemy . github .io.
  • TsvetoslavTsekov has worked for 5 years on various software development projects - desktop applications, backend applications, WinCE embedded software, RESTful APIs. He then became exceedingly interested in Artificial Intelligence and particularly Deep Learning. After receiving his Deep Learning Nanodegree, he has worked on numerous projects - Image Classification, Sport Results Prediction, Fraud Detection, and Machine Translation. He is also very interested in General AI research and is always trying to stay up to date with the cutting-edge developments in the field.

Who this course is for:

  • This Learning Path is geared towards software developers and machine learning enthusiasts who would like to improve their skills and expertise in machine learning and more specifically deep learning.

Report abuse