All these tutorial are written by me as a freelancing working for tutorial project AlgoDaily. These has been slightly changed and more lessons after lesson 12 has been added to the actual website. Thanks to Jacob, the owner of AlgoDaily, for letting me author such a wonderful Machine Learning tutorial series. You can sign up there and get a lot of resources related to technical interview preparation.

# Machine Learning Series structure

In this page, I am going to introduce to machine learning basics over 12 lessons. Unlike all other tutorials, I will not explain how important it is to learn machine learning. If you are here, you already know about it and want to dig straight into how to do it. So let’s get started. The overall structure of this tutorial is given below.

## Lesson 1: Introduction to Machine Learning

- What is Machine Learning
- Prerequisites.
- Brief overview of Python
- 10 Example Applications of ML
- Core packages that will be covered in the series: Python, Numpy, OpenCV, Scikit-Learn, Scikit-Image, Tensorflow & PyTorch
- Warming up Python Skills
- Jupyter Notebook, Python Setup, Conda, Virtualenv
- Finally end with a fun linear regression model from scratch.

## Lesson 2: All about Numpy and Pandas

- Matrix and Data
- Dimensions and Shapes of numpy
`ndarray`

. - Broadcasting in numpy
- Pandas and Numpy differences
- Using lambda on numpy and pandas.

## Lesson 3: Supervised learning and unsupervised learning; Instance based learning and object based learning

- Data and their Labels
- Batch and Online learning
- Linear Regression
- Dataset divided into train and test

## Lesson 4: Machine Learning basic from scratch

- Hyperparameter tuning and Model Selection
- Linear Regression from scratch
- Gradient Descendent Algorithm

## Lesson 5: Statistics in Machine Learning

- Matplotlib
- Plotly

## Lesson 6: Data Visualization

- Probabilistic Model
- Data Distributions
- Data Preprocessing
- Normalization and Standardization
- Hypothesis Testing (student’s T-test)

## Lesson 7: All about Scikit-Learn (Supervised Learning only)

- Binary/Multiclass Classification, Detection, Recognition etc.
- Logistic Regression, Linear Regression, Polynomial Regression, Activation Function etc.
- SVM, Decision Tree, Ensemble learning, Random Forest

## Lesson 7.5: All about Scikit-Learn (UnSupervised Learning only)

- Dimensionality, PCA, t-SNE, KNN etc.
- K-means, Clustering, DBSCAN etc.

## Lesson 8: Neural Networks Basics

## Lesson 9: Introduction to TensorFlow

## Lesson 10?: Advanced Deep Learning Networks

- Image Processing
- OpenCV
- CNN
- Finding dataset
- Finding models

## Lesson 11: Trying out popular Deep Learning Models

- Popular models and their implementation in python
- Yolo
- Inception
- Residual Net
- Alex NET
- GANs

- GTP3