NewAdventures

October 8, 2018

Part of the Deep Learning (Machine Learning) Category

Note: [**] indicates Python3 Script or Jupyter Notebook ran fine

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 – http://timeoutofmind.com/wordpress/?p=6349  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?
  14. H2O.ai
  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
• Related: MIT AGI: Computational Universe (Stephen Wolfram) – Completed March 4, 2018
• Why data scientists should start learning Swift – Completed April 29, 2018
• Swift for TensorFlow – TFiwS (TensorFlow Dev Summit 2018) – Completed April 29, 2018
• 5 Techniques To Understand Machine Learning Algorithms Without the Background in Mathematics: Completed all 11 Chapters as of May 22, 2018
  1. Machine Learning for Programmers – Completed May 8, 2018
  2. Practice Machine Learning with Datasets from the UCI Machine Learning Repository – Completed May 9, 2018
  3. Take Control By Creating Targeted Lists of Machine Learning Algorithms – Completed May 11, 2018
     1. I ran my first Weka session today using: How to Run Your First Classifier in Weka. It is very cool! – Completed May 11, 2018
  4. How to Research a Machine Learning Algorithm – Completed on May 13, 2018
  5. How to Learn a Machine Learning Algorithm – Completed May 14, 2018
  6. Clever Algorithms: Nature-Inspired Programming Recipes – Completed May 15, 2018
  7. How To Investigate Machine Learning Algorithm Behavior – Completed May 16, 2018
  8. How to Implement a Machine Learning Algorithm – Completed May 19, 2018
  9. Benefits of Implementing Machine Learning Algorithms From Scratch – Completed May 21, 2018
  10. Don’t Start with Open-Source Code When Implementing Machine Learning Algorithms – Completed May 22, 2018
• A Gentle Introduction to the Law of Large Numbers in Machine Learning – Completed on May 19, 2018
• Conversational Machine Learning – Tom Mitchell – Completed May 19, 2018
• Back to the Edge: AI Will Force Distributed Intelligence Everywhere – Completed May 24, 2018
• An in-depth look at Google’s first Tensor Processing Unit (TPU) – Completed May 24, 2018
• Learning: Support Vector Machines (MIT 6.034 Artificial Intelligence, Fall 2010) – Completed on May 24, 2018
• Machine Learning for Humans:
  1. Why Machine Learning Matters – Completed May 21, 2018
  2. Supervised Learning I  – Completed May 22, 2018
  3. Supervised Learning II – Completed May 23, 2018
  4. Supervised Learning III – Completed May 24, 2018
  5. Unsupervised Learning – Completed May 26, 2018
  6. Neural Networks & Deep Learning – Completed May 28, 2018
  7. Reinforcement Learning – Completed May 30, 2018
     1. Appendix: The Best Machine Learning Resources
• Google’s AutoML will change how businesses use Machine Learning – Completed May 28, 2018
• Swift for TensorFlow (Github Project using Xcode 4.1) – Completed May 30, 2018
• How to build an image recognition iOS app with Apple’s CoreML and Vision APIs (Github Project using Xcode 4.1) – Completed May 31, 2018
• Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data – June 6, 2018
• A Neural Network Playground – Completed June 6, 2018
•  TensorFlow and deep learning, without a PhD – Partially completed June 6, 2018
• Deep Learning with Anaconda and Online Studies: Started June 24, 2018
  • Today I installed Anaconda on my 2015 iMac and successfully ran the example inputs, correctly obtaining the random calculated outputs from the Python 3 scripts on this example: How to Calculate the 5-Number Summary for Your Data in Python. [**]
    • I did a great deal of online research pertaining to Anaconda these last few days in preparation for this important step in actual work with Data Qualification with respect to Deep Learning.
    • My experiences with Deep Learning should accelerate now that I have a better understanding of that topic and some software tools to use in my office. – Completed June 24, 2018
• Machine Learning Cheatsheet – Added June 27, 2018
• Machine Learning week 1: Cost Function, Gradient Descent and Univariate Linear Regression – Partially completed June 27, 2018
• Cost Function Explained – Completed June 27, 2018 [**]
• Tensorflow: The Confusing Parts (1) – Completed June 28, 2018 [**]
  • Graphs and Sessions – ( Optional )
• Linear Regression – Completed June 29, 2018 [**]
• Rectified Linear Units (ReLU) in Deep Learning –  Completed July 1, 2018
• Deep Learning with Python – Completed July 1, 2018 [**]
• Intuition of Gradient Descent for Machine Learning – Completed July 2, 2018 [**]
  • 6. Gradient Descent Intuition (Optional)
  • 7. Gradient Descent for Linear Regression (Optional)
• Over 150 of the Best Machine Learning, NLP, and Python Tutorials I’ve Found – Added July 12, 2018
• A Complete Machine Learning Project Walk-Through in Python: Part One – Completed July 13, 2018 [**]
• A Complete Machine Learning Project Walk-Through in Python: Part Two – Completed July 14, 2018 [**]
• A Complete Machine Learning Walk-Through in Python: Part Three – Completed July 15, 2018 [**]
• Quick guide to understand the hype around ‘deep learning’ – Completed July 16, 2018
• The Art of Effective Visualization of Multi-dimensional Data – Completed July 28, 2018 [**]
• AutoGraph converts Python into TensorFlow graphs – Completed July 28, 2018 [**]
• Quick (and free) experiment for CPU vs GPU for Deep Learning – Completed August 6, 2018 [**]
• Quick dive into Pandas for Data Science – Completed August 11, 2018
• How to Run Parallel Data Analysis in Python using Dask Dataframes – Completed September 6, 2018 [**]
• Hyperparameter Optimization with Keras – Added September 13, 2018
• An Overview of Monte Carlo Methods – Added September 13, 2018
• Essential Cheat Sheets for Machine Learning and Deep Learning Engineers – Added September 17, 2018
• A “Data Science for Good“ Machine Learning Project Walk-Through in Python: Part One – Completed September 17, 2018 [**]
• Deep Dive into Math Behind Deep Networks Mysteries of Neural Networks, Part I – Added September 18, 2018
• The Deep Learning(.ai) Dictionary – Added September 20, 2018
• Linear Regression using Gradient Descent – Added September 20, 2018 [**]
• Multi Label Text Classification with Scikit-Learn – Completed September 22, 2018 [**]
• Added PyTorch Section – October 8, 2018