Deep Learning (Machine Learning )Education Studies

March 4, 2018

It takes time and effort to keep skills as fresh as possible. My LinkedIn Home Page contains my long listing of educational pursuits.

Recently I became interested in learning about Artificial Intelligence (AI) using some Deep Learning (Machine Learning) online courses. Some are shown below:

Along the way I captured 12 Deep Learning Model web links for further exploration as time allows.

  • Deep Learning SIMPLIFIED : Completed all 30 YouTube videos of the Series. Each video had a steep learning curve. Along the way I captured 12 Deep Learning Model web links for further exploration as time allows.”Deep Learning is an important subfield of Artificial Intelligence (AI) that connects various topics like Machine Learning, Neural Networks, and Classification. The field has advanced significantly over the years due to the works of giants like Andrew Ng, Geoff Hinton, Yann LeCun, Adam Gibson, and Andrej Karpathy. Many companies have also invested heavily in Deep Learning and AI research – Google with DeepMind and its Driverless car, nVidia with CUDA and GPU computing, and recently Toyota with its new plan to allocate one billion dollars to AI research.”Follow my enumerated progress on my blog –  as of November 27, 2017
    1. The Series Intro
    2. What is a Neural Network
    3. 3 reasons to go Deep
    4. Your choice of Deep Net
    5. An Old Problem
    6. Restricted Boltzmann Machines
    7. Deep Belief Nets
    8. Convolutional Neural Networks
    9. Recurrent Neural Networks
    10. Autoencoders
    11. Recursive Neural Tensor Nets
    12. Use Cases
    13. What is a Deep Net Platform?
    15. Dato GraphLab
    16. What is a Deep Learning Library?
    17. Theano
    18. Deeplearning4j
    19. Torch
    20. Caffe
    21. How good is your fit?
    22. TensorFlow
    23. Metrics
    24. Deep Net Performance
    25. Text Analytics
    26. Configuring a Deep net
    27. Transfer Learning with Indico
    28. Neural Storyteller with Somatic
    29. Inceptionism with Somatic
    30. Reinforcement Learning
  • Neural Networks and Deep Learning : Completed all 6 Chapters as of December 4, 2017. I understood about 15-20% of this very sophisticated information
    1. Using neural nets to recognize handwritten digits
    2. How the backpropagation algorithm works [ Skipped for the time being ]
    3. Improving the way neural networks learn
    4. A visual proof that neural nets can compute any function
    5. Why are deep neural networks hard to train?
    6. Deep Learning
  • Lecture—  Theoretical Machine Learning Lecture Series: Deep Learning and Cognition  December 6, 2017
  • Lecture— Android meets TensorFlow – PyData Singapore December 9, 2017
  • 3Blue1Brown Channel for Neural Networks:
    1. But what *is* a Neural Network? | Chapter 1, deep learning – Completed February 3, 2018
    2. Gradient descent, how neural networks learn | Chapter 2, deep learning – Completed February 3, 2018
    3. What is backpropagation really doing? | Chapter 3, deep learning – Completed February 3, 2018
    4. Backpropagation calculus | Appendix to deep learning chapter 3 – Completed February 5, 2018
  • RelatedMIT AGI: Computational Universe (Stephen Wolfram) – Completed March 4, 2018
Did you like this? Share it:

About Don Larson

Using computer technology since June 1980.
This entry was posted in Deep Learning (Machine Learning), Education, Personal. Bookmark the permalink.