Basic path to learn Practical Machine Learning.

Prerequisite

  • High school math(vectors, matrices, calculus, probability, and stats)
  • Basic Python Help.
  • Must have Patience to learn new things.

Motivation

  1. Watch AI For Everyone By Andrew Ng

    • The meaning behind common AI terminology, including neural networks, machine learning, deep learning, and data science.
    • What AI realistically can–and cannot–do.
    • How to spot opportunities to apply AI to problems in your own organization.
    • What it feels like to build machine learning and data science projects.
    • How to work with an AI team and build an AI strategy in your company.
    • How to navigate ethical and societal discussions surrounding AI.

  2. YouTube Originals AGE OF AI

    How AI is used in real life.

Started learning

Step-0

  1. Understand basic of machine learning
    • Supervised Learning
    • Unsupervised Learning
    • Classification and Regression
  2. Learn python and some useful library
    • Pandas

      Pandas is a popular Python library for data analysis.

    • NumPy

      NumPy is a very popular python library for large multi-dimensional array and matrix processing.

    • Matplotlib

      Matpoltlib is a very popular Python library for data visualization.

  3. Setup Local Machine with latest Anaconda

    Anaconda is a free and open-source distribution of the Python and R.

Step-1

  1. How to use data from verious source like [Kaggle UCI ml repo].

  2. Start to use Jupyter notebook A complate IDE for data science and machine learning.

  3. Started hand on practice with scikit-learn.

  4. Use scikit-learn map and documentation.

Step-2

  • Now, you are a little bit comfortable with coding it’s time to learn basic maths behind those algorithms.

  • Take a Andrew’s Course.

Step-3

  • Learn about Deep-learning.

  • Learn about popular library [TensorFlow PyTorch]
    • TensorFlow is backed by Google Brain team.
    • PyTorch is developed by Facebook’s AI Research lab.
    • Both have large community.
    • There are other librarys as well like Theano, Keras, Caffe, Apache MXNet and many more.
  • In neural network learn
    1. ANN (artificial neural network)
    2. CNN (Convolutional neural network)
    3. RNN (Recurrent neural networks)
    4. Autoencoder

Happy coding and have a great time learning how to make machines smarter.