Skip to content

Latest commit

 

History

History
188 lines (91 loc) · 4.23 KB

syllabus.md

File metadata and controls

188 lines (91 loc) · 4.23 KB

Machine Learning 3 Months Course

Month 1

Week 1

  1. Matrix

  • Rank of Matrix
  • Matrix Multiplication
  • Matrix Transformation
  • Matrix Transformation in Image

  1. Metrics

  • Metrics of Model
  • Confusion Matrix

  1. Statistics

  • Population and Sampling
  • Normal Distribution
  • Z-score
  • Chi Square test

  1. Probability

  • Conditional Probability
  • Bayes’ Theorem

  1. Calculus

  • Derivatives
  • Integration

  1. Numpy Basics

  2. Pandas basic

  3. Matplotlib and Seaborn

Main Resource [ Theory ]: Mathematics for Machine Learning

Numpy basic: https://colab.research.google.com/github/cs231n/cs231n.github.io/blob/master/python-colab.ipynb?fbclid=IwAR2FhLFWc35SsA6hzUgnBDxaaNhe08bCg1D3QjvYjgpUgzH4CPkp4yjA0x4#scrollTo=0vJLt3JRL9eR

Week 2:

Scikit Algorithms

  1. Naive Bayes

  2. K means clustering

  3. Support Vector Machine ( svm)

  4. Knn classification

  5. Random Forest

Advance:

Pandas alternative to GPU: Open GPU Data Science | RAPIDS

Resources:

  1. 3Blue1Brown

  2. Mathematics for Machine Learning

  3. Geometric Transformations of Images

  4. https://www.datacamp.com/community/tutorials/naive-bayes-scikit-learn(Naive Bayes)

Week 3 : Machine learning

  1. Preprocessing Data

  2. XGboost Basics

  3. Opencv Basics

  4. Time series Data

Week 4

  1. Topic Frequency-Inverse Document Frequency (TF-IDF)

  2. Singular Value Decomposition (SVD)

  3. Non-negative Matrix Factorization (NMF)

  4. Stochastic Gradient Descent (SGD)

  5. Truncated SVD

Main Resource [ Code ]: https://github.com/fastai/numerical-linear-algebra/blob/master/README.md



Month 2

Google Machine learning crash course for month 2: https://developers.google.com/machine-learning/crash-course/ml-intro

Week 1

  1. Intro to keras

  2. PCA - Python implementation

  3. Month 1 Learning Recap

Resources: StatQuest: Principal Component Analysis (PCA), Step-by-Step

Intro to keras : https://colab.research.google.com/drive/1qKPITTI879YHTxbTgYW_MAWMHFkbOBIk

Week 2

  1. Cuda Programming Basics

  2. Intro to Tensorflow

  3. Intro to Pytorch

Resources: How Convolutional Neural Networks work

Week 3 : Deep learning

  1. CNN implementation

  2. Hugging face - Text models usage

  3. Pytorch Basics: Pretrained Models

  4. Tensorflow Basics : pretrained Models

Week 4

  1. Resnet 50 implementation

  2. Transfer Learning

  3. Detectron2 implementation



Month 3

Week 1

  1. NN encode and Decoder

  2. GAN

  3. Style Transfer

  4. Text Generation

Week 2

  1. Recurrent Neural Network

  2. Reinforcement Learning

Week ¾ : Project

Paper Implementation / Project

Explore More deeper :

https://montrealartificialintelligence.com/academy/