Modern Deep Learning in Python

This course continues where my first course, Deep Learning in Python, left off. You already know how to build an artificial neural network in Python, and you have a plug-and-play script that you can use for TensorFlow. Neural networks are one of the staples of machine learning, and they are always a top contender in Kaggle contests. If you want to improve your skills with neural networks and deep learning, this is the course for you.

You already learned about backpropagation, but there were a lot of unanswered questions. How can you modify it to improve training speed? In this course you will learn about batch and stochastic gradient descent, two commonly used techniques that allow you to train on just a small sample of the data at each iteration, greatly speeding up training time.

You will also learn about momentum, which can be helpful for carrying you through local minima and prevent you from having to be too conservative with your learning rate. You will also learn about adaptive learning rate techniques like AdaGrad, RMSprop, and Adam which can also help speed up your training.

Because you already know about the fundamentals of neural networks, we are going to talk about more modern techniques, like dropout regularization and batch normalization, which we will implement in both TensorFlow and Theano. The course is constantly being updated and more advanced regularization techniques are coming in the near future.

In my last course, I just wanted to give you a little sneak peak at TensorFlow. In this course we are going to start from the basics so you understand exactly what's going on - what are TensorFlow variables and expressions and how can you use these building blocks to create a neural network? We are also going to look at a library that's been around much longer and is very popular for deep learning - Theano. With this library we will also examine the basic building blocks - variables, expressions, and functions - so that you can build neural networks in Theano with confidence.

Theano was the predecessor to all modern deep learning libraries today. Today, we have almost Keras, PyTorch, CNTK (Microsoft), MXNet (Amazon / Apache), etc. In this course, we cover all of these. Pick and choose the one you love best.

Because one of the main advantages of TensorFlow and Theano is the ability to use the GPU to speed up training, I will show you how to set up a GPU-instance on AWS and compare the speed of CPU vs GPU for training a deep neural network.

With all this extra speed, we are going to look at a real dataset - the famous MNIST dataset (images of handwritten digits) and compare against various benchmarks. This is THE dataset researchers look at first when they want to ask the question, "does this thing work?"

These images are important part of deep learning history and are still used for testing today. Every deep learning expert should know them well.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

NOTES:

All the code for this course can be downloaded from my github: /lazyprogrammer/machine_learning_examples

In the directory: ann_class2

Make sure you always "git pull" so you have the latest version.

  • Take handwritten notes. This will drastically increase your ability to retain the information.
  • Write down the equations. If you don't, I guarantee it will just look like gibberish.
  • Ask lots of questions on the discussion board. The more the better.
  • Realize that most exercises will take you days or weeks to complete.
  • Write code yourself, don't just sit there and look at my code.
  • :

    • Check out the lecture "What order should I take your courses in?" (available in the Appendix of any of my courses, including the free Numpy course)

    Get Details and Enroll Now

    OpenCourser is an affiliate partner of Udemy.

    Get a Reminder

    Not ready to enroll yet? We'll send you an email reminder for this course

    Send to:

    Udemy

    Rating 4.4 based on 164 ratings
    Length 9 hours
    Starts On Demand (None)
    Cost $11
    From Udemy
    Instructor Lazy Programmer Inc.
    Free Limited Content
    Language English
    Subjects Business Data Science
    Tags Business Data & Analytics

    Get a Reminder

    Get an email reminder about this course

    Send to:

    What people are saying

    We analyzed reviews for this course to surface learners' thoughts about it

    neural network in 11 reviews

    For anyone who wants practical ways of speeding up training in a deep neural network you should watch these lectures.

    learning very practical neural network training tips excellent coverage of the dropout algorithim Good content, well explained but you need some experience with this to understand clearky whats going on.

    This material of this course is must-know before progressing to more advanced neural network architectures.

    neural networks in 8 reviews

    These are great once you know the basic of neural networks.

    This is a great course for expanding on basic neural networks concepts.

    course is right on the topic of making practical neural networks.

    great to see all these different methods of training neural networks packed into one course.

    pca) Good course for scaling up neural networks.

    Great course for learning how to optimize neural networks.

    Easy to grasp if you know about neural networks and you want to learn all the new deep learning tricks of the trade.

    theano and tensorflow in 7 reviews

    good so far :) superb just great good intro to theano and tensorflow Up to now I just got overview and advertisement not real knowledge problem yet even though there's not much math in the course, i feel this class is the most confusing of the series thus far.

    The course takes into account all basic aspects of Theano and Tensorflow.

    He introduces theano and tensorflow well and discusses the advantages/disadvantages of each.

    The course is dense, showing the implementations of the same examples in Theano and Tensorflow, so one can see the differences between the two frameworks easy.

    this course teaches helpful techniques to improve backpropagation and theano and tensorflow coding I like how the instructor provides only the source code necessary to learn the concepts.

    This doesn't teach much about Theano or TensorFlow except just showing the example code... lots of practical tips included and includes great tutorials on theano and tensorflow Good practical course with details on both Theano and Tensorflow.

    lazy programmer in 7 reviews

    This course was another great course by “The Lazy Programmer”.

    I’ve done numerous other courses on Deep Learning and i have again come back to a Lazy Programmer application and found a more grounded and real base for my learning.

    I like that part of Lazy programmer series of courses.

    Super like all courses by Lazy Programmers!!!

    All the lazy programmer courses are done very well, they give complete preparation but they are very challenging; their sequence forms a pleasant and complete course path; congratulations to the author.

    again, lazy programmer explains complex stuff in a simple way that anybody can understand, without the complex math matters, which sometimes makes things unreadable.

    Lazy programmer teaches a great course.

    I miss explanations about the code, the theory is only shallowly explained and there are no exercises... very concise and informative good breadth of more advanced deep learning techniques awesome followup to the original deep learning course As usual, the Lazy Programmer explains it well for you, doesn't spoon feed, and makes you learn the material.

    modern deep learning in 5 reviews

    Good course to deep learning on ANN It talks about a huge number of modern deep learning topics and associated implementations.

    This course was the perfect introduction to modern deep learning concepts.

    It shows how to implement Python code for modern deep learning algorithms like dropout and rmsprop.

    This is a great introduction to modern deep learning and neural networks packaged into a neatly organized course and simple effective explanations.

    One of the best courses I have taken on deep learning, taking you from MLPs to modern deep learning.

    more advanced in 4 reviews

    The lectures begin with simple review material and get more advanced deep into the course.

    eager to work on MNIST and apply to other real world problems great followup to the original course the previous course sets you up perfectly to learn these more advanced concepts with ease.

    Careers

    An overview of related careers and their average salaries in the US. Bars indicate income percentile.

    Learning Services $59k

    Computer Vision, Deep Learning Engineer $67k

    Computer Vision & Deep Learning Engineer $67k

    Deep Clean Sales Specialist $76k

    Deep clean specialist $76k

    Deep Learning Research Scientist $86k

    Deep Learning Research Engineer $88k

    Research Scientist - Deep Learning $91k

    Senior Learning Specialist, Learning and Development $102k

    Deep Learning R&D Engineer $127k

    Learning Assitant $142k

    Deep Submergence Systems Program Manager $157k

    Write a review

    Your opinion matters. Tell us what you think.

    Udemy

    Rating 4.4 based on 164 ratings
    Length 9 hours
    Starts On Demand (None)
    Cost $11
    From Udemy
    Instructor Lazy Programmer Inc.
    Free Limited Content
    Language English
    Subjects Business Data Science
    Tags Business Data & Analytics