Skip to content

Latest commit

 

History

History
100 lines (76 loc) · 4.69 KB

README.md

File metadata and controls

100 lines (76 loc) · 4.69 KB
Raw

Goal: Machine Learning

To achieve proficiency in data science and machine learning, follow this structured learning path:

1. Getting started

1.1. Prerequesties

1.1.1. Mathematics Fundamentals:

  • Algebra

    • Variables, coefficients, and functions
    • Linear equations
    • Logarithms
    • Sigmoid function

  • Linear Algebra

    • tensor and tensor rank
    • matrix multiplication

  • Trigonometry

    • tanh (discussed as an activation function; no prior knowledge needed)

  • Statistics

    • mean, median, outliers, and standard deviation
    • ability to read a histogram

  • Calculus (Optional, for advanced topics)

    • concept of a derivative (you won't have to actually calculate derivatives)
    • gradient or slope
    • partial derivatives (which are closely related to gradients)
    • chain rule (for a full understanding of the backpropagation algorithm for training neural networks)

1.1.2. Programming with Python and Libraries:

  • Learn Python and mainly these things
  • libraries like NumPy and Pandas.

1.1.3. Machine Learning Algorithms:

  • Understand supervised, unsupervised, and reinforcement learning.
  • Study algorithms such as Linear Regression, Logistic Regression, Clustering, KNN, SVM, Decision Trees, Random Forests.
  • Explore concepts like overfitting, underfitting, regularization, gradient descent, and confusion matrix.

1.1.4. Data Preprocessing:

  • Handle null values.
  • Standardize data.
  • Deal with categorical values and perform one-hot encoding.
  • Apply feature scaling.

1.1.5. Machine Learning Libraries:

  • Get familiar with popular libraries like scikit-learn, Matplotlib, and TensorFlow.

1.1.6. Practical Experience:

  • Participate in Kaggle competitions and practice on real-world datasets.
  • Explore projects on GitHub for learning from others' code.

1.2. Resources:

  • Maths:

    • Linear Algebra notes by P. J. Cameron (Link)
    • Statistics and Probability resource (Link)
    • YouTube playlist on Maths (Link)
    • Mathematics for Machine Learning (link)

  • Machine Learning:

    • Google's Machine Learning Crash Course (Link) - This is a great resource for learning the fundamentals of machine learning. It's a free course that covers the theory and practice of ML, including basic concepts like loss function and gradient descent, and also more advanced concepts like training neural networks and recommender systems.
    • Coursera: Machine Learning by Andrew Ng (Stanford University) (Link)
    • Made With ML (Link)
    • Machine Learning Mastery (Link)

  • Data Preprocessing:

    • Data Preprocessing in Machine Learning (Link)

  • Machine Learning Libraries:

    • scikit-learn documentation (Link)
    • TensorFlow documentation (Link)

  • Practice Platforms:

  • Other prerequesties

    To run the programming exercises on your local machine or in a cloud console, you should be comfortable working on the command line:

Follow this roadmap, practice consistently, and explore projects to develop your skills in data science and machine learning. Good luck on your learning journey! This readme was created by @CodeWhiteWeb after contacting many professionals in this field.