Master Deep Learning with TensorFlow in Python
  • ondemand_video
       Video Length : 20h10m0s
  • format_list_bulleted
       Tasks Number : 136
  • group
       Students Enrolled : 1412
  • equalizer
       Medium Level
  • Curriculum
  • 1. Course introduction
    • videocam
      Meet your instructors and why you should study machine learning?
      10m0s
    • videocam
      What does the course cover?
      10m0s
    • videocam
      What does the course cover? - Quiz
      10m0s
  • 2. Introduction to neural networks
    • videocam
      Introduction to neural networks
      10m0s
    • videocam
      Introduction to neural networks - Quiz
      10m0s
    • videocam
      Training the model
      10m0s
    • videocam
      Training the model - Quiz
      10m0s
    • videocam
      Types of machine learning
      10m0s
    • videocam
      Types of machine learning - Quiz
      10m0s
    • videocam
      The linear model
      10m0s
    • videocam
      The linear model - Quiz
      10m0s
    • videocam
      Need Help with Linear Algebra?
      10m0s
    • videocam
      The linear model. Multiple inputs
      10m0s
    • videocam
      The linear model. Multiple inputs - Quiz
      10m0s
    • videocam
      The linear model. Multiple inputs and multiple outputs
      10m0s
    • videocam
      The linear model. Multiple inputs and multiple outputs - Quiz
      10m0s
    • videocam
      Graphical representation
      10m0s
    • videocam
      Graphical representation - Quiz
      10m0s
    • videocam
      The objective function
      10m0s
    • videocam
      The objective function - Quiz
      10m0s
    • videocam
      L2-norm loss
      10m0s
    • videocam
      L2-norm loss - Quiz
      10m0s
    • videocam
      Cross-entropy loss
      10m0s
    • videocam
      Cross-entropy loss - Quiz
      10m0s
    • videocam
      One parameter gradient descent
      10m0s
    • videocam
      One parameter gradient descent - Quiz
      10m0s
    • videocam
      N-parameter gradient descent
      10m0s
    • videocam
      N-parameter gradient descent - Quiz
      10m0s
  • 3. Setting up the working environment
    • videocam
      Setting up the environment - An introduction - Do not skip, please!
      10m0s
    • videocam
      Why Python and why Jupyter?
      10m0s
    • videocam
      Why Python and why Jupyter? - Quiz
      10m0s
    • videocam
      Installing Anaconda
      10m0s
    • videocam
      The Jupyter dashboard - part 1
      10m0s
    • videocam
      The Jupyter dashboard - part 2
      10m0s
    • videocam
      Jupyter Shortcuts
      10m0s
    • videocam
      The Jupyter dashboard - Quiz
      10m0s
    • videocam
      Installing the TensorFlow package
      10m0s
    • videocam
      Installing packages - exercise
      10m0s
    • videocam
      Installing packages - solution
      10m0s
  • 4. Minimal example - your first machine learning algorithm
    • videocam
      Minimal example - part 1
      10m0s
    • videocam
      Minimal example - part 2
      10m0s
    • videocam
      Minimal example - part 3
      10m0s
    • videocam
      Minimal example - part 4
      10m0s
    • videocam
      Minimal example - Exercises
      10m0s
  • 5. TensorFlow - An introduction
    • videocam
      TensorFlow outline
      10m0s
    • videocam
      TensorFlow intro
      10m0s
    • videocam
      Types of file formats in TensorFlow
      10m0s
    • videocam
      Inputs, outputs, targets, weights, biases - model layout
      10m0s
    • videocam
      Loss function and gradient descent - introducing optimizers
      10m0s
    • videocam
      Model output
      10m0s
    • videocam
      Minimal example - Exercises
      10m0s
  • 6. Going deeper: Introduction to deep neural networks
    • videocam
      Layers
      10m0s
    • videocam
      What is a deep net?
      10m0s
    • videocam
      Understanding deep nets in depth
      10m0s
    • videocam
      Why do we need non-linearities?
      10m0s
    • videocam
      Activation functions
      10m0s
    • videocam
      Softmax activation
      10m0s
    • videocam
      Backpropagation
      10m0s
    • videocam
      Backpropagation - visual representation
      10m0s
  • 7. Backpropagation. A peek into the Mathematics of Optimization
    • videocam
      Backpropagation. A peek into the Mathematics of Optimization
      10m0s
  • 8. Overfitting
    • videocam
      Underfitting and overfitting
      10m0s
    • videocam
      Underfitting and overfitting - classification
      10m0s
    • videocam
      Training and validation
      10m0s
    • videocam
      Training, validation, and test
      10m0s
    • videocam
      N-fold cross validation
      10m0s
    • videocam
      Early stopping
      10m0s
  • 9. Initialization
    • videocam
      Initialization - Introduction
      10m0s
    • videocam
      Types of simple initializations
      10m0s
    • videocam
      Xavier initialization
      10m0s
  • 10. Gradient descent and learning rates
    • videocam
      Stochastic gradient descent
      10m0s
    • videocam
      Gradient descent pitfalls
      10m0s
    • videocam
      Momentum
      10m0s
    • videocam
      Learning rate schedules
      10m0s
    • videocam
      Learning rate schedules. A picture
      10m0s
    • videocam
      Adaptive learning rate schedules
      10m0s
    • videocam
      Adaptive moment estimation
      10m0s
  • 11. Preprocessing
    • videocam
      Preprocessing introduction
      10m0s
    • videocam
      Basic preprocessing
      10m0s
    • videocam
      Standardization
      10m0s
    • videocam
      Dealing with categorical data
      10m0s
    • videocam
      One-hot and binary encoding
      10m0s
  • 12. The MNIST example
    • videocam
      The dataset
      10m0s
    • videocam
      How to tackle the MNIST
      10m0s
    • videocam
      Importing the relevant packages
      10m0s
    • videocam
      Outlining the model
      10m0s
    • videocam
      Declaring the loss and the optimization algorithm
      10m0s
    • videocam
      Accuracy of prediction
      10m0s
    • videocam
      Batching and early stopping
      10m0s
    • videocam
      Learning
      10m0s
    • videocam
      Discuss the results and test
      10m0s
    • videocam
      MNIST - exercises
      10m0s
    • videocam
      MNIST - solutions
      10m0s
  • 13. Business case
    • videocam
      Exploring the dataset and identifying predictors
      10m0s
    • videocam
      Outlining the business case solution
      10m0s
    • videocam
      Balancing the dataset
      10m0s
    • videocam
      Preprocessing the data
      10m0s
    • videocam
      Preprocessing exercise
      10m0s
    • videocam
      Create a class for batching
      10m0s
    • videocam
      Outlining the model
      10m0s
    • videocam
      Optimizing the algorithm
      10m0s
    • videocam
      Interpreting the result
      10m0s
    • videocam
      Testing the model
      10m0s
    • videocam
      A comment on the homework
      10m0s
    • videocam
      Final exercise
      10m0s
  • 14. Appendix: Linear Algebra Fundamentals
    • videocam
      What is a Matrix?
      10m0s
    • videocam
      Scalars and Vectors
      10m0s
    • videocam
      Linear Algebra and Geometry
      10m0s
    • videocam
      Scalars, Vectors and Matrices in Python
      10m0s
    • videocam
      Tensors
      10m0s
    • videocam
      Addition and Subtraction of Matrices
      10m0s
    • videocam
      Errors when Adding Matrices
      10m0s
    • videocam
      Transpose of a Matrix
      10m0s
    • videocam
      Dot Product of Vectors
      10m0s
    • videocam
      Dot Product of Matrices
      10m0s
    • videocam
      Why is Linear Algebra Useful?
      10m0s
  • 15. Conclusion
    • videocam
      See how much you have learned
      10m0s
    • videocam
      What’s further out there in the machine and deep learning world
      10m0s
    • videocam
      An overview of CNNs
      10m0s
    • videocam
      How DeepMind uses deep learning
      10m0s
    • videocam
      An overview of RNNs
      10m0s
    • videocam
      An overview of non-NN approaches
      10m0s
Authors

Kevin Gautama is a systems design and programming engineer with 16 years of expertise in the fields of electrical and electronics and information technology.

He teaches at the Hanoi University of Industry in the period 2003-2011 and he has a certificate of vocational training by the Ministry of Industry and Commerce and the Hanoi University of Industry.

From extensive design experience through numerous engineering projects, the author founded the Enziin Academy.

The Enziin Academy is a startup in the field of educational, it's core goal is to training design engineers in the fields technology related.

The Enziin Academy is headquartered in Stockholm-Sweden with an orientation operating multi-lingual and global.

The author's skills in IT:

  • Implementing the application infrastructure on Amazon's cloud computing platform.
  • Linux server system administration (Sysadmin).
  • Design load balancing and content distribution system.
  • MySQL database administration.
  • C/C++/C# Programming
  • Ruby and Ruby on Rails Programming
  • Python and Django Programming
  • The WPF/C# on the .NET Framework Programming
  • The PHP/JAVA Programming
  • Machine Learning and Expert System.
  • Internet of Things.

The author's skills in the fields of electric and electronic:

  • The design of popular CPU / MCU systems.
  • Design FPGA / CPLD system (Xilinx - Altera).
  • Design and programming of DSP systems (Texas Instruments).
  • Embedded ARM system design.
  • The RTOS Programming
  • Design and programming electronic power systems.
  • PLC - inverter - sensor - electric control cabinet industrial.
  • Control systems distributed connection with Server.

Read more...

Master Deep Learning with TensorFlow in Python


Master Deep Learning with TensorFlow in Python

Discussions
You must login to comment.