Curriculum

1. Introduction

   1 lesson

   1. About the Diploma

2. 01 Welcome

   3 lessons

   1. 02 ML Welcome A
   2. 02 ML Welcome B
   3. 03 ML Intro - Data DS and ML

3. 02 Inroduction

   2 lessons

   1. 04 Background - Gaussian Line and Graph
   2. 05 Background Calculus - Intro remain

4. 03 Libraries

   2 lessons

   1. 06 Quiz 1 - Libraries Scikit- Jupyter - Numpy
   2. 07 Matplotlip - Pandas

5. 04 Linear Regression

   6 lessons

   1. 08 Pandas - Linear Regression
   2. 09 Gradient Descent 1
   3. 10 Gradient Descent 2
   4. 11 Linear Regression with Gradient Descent 1
   5. 12 Linear Regression with Gradient Descent 2
   6. 13 Linear Regression with Gradient Descent 2

6. Homework 1 - Gradient Descent - 2 subtasks

   2 lessons

   1. 06 Gradient Descent Homework - 2 subtasks
   2. 06 Gradient Descent Homework - Solution

7. 05 Modeling and Data Concepts

   17 lessons

   1. 13 Liner Regression Codes - Polynomial Regression Intro
   2. 14 Polynomial Regression - Model Selection
   3. 15 Model Selection - Data Collection Task
   4. 16 Data task sol part 1 - quiz 2 answer
   5. 17 Model Selection - Cross Validation
   6. 18 Data Collection Task 2
   7. 19 Data Collection Task 3
   8. 20 Cross Validation - Overfitting
   9. 21 Pipeline Concerns and Modeling - Overfitting
   10. 22 Quiz 3 - Ridge
   11. 23 Ridge
   12. 24 Lasso
   13. 25 Bias-Variance Tradeoff - Homework2
   14. 26 Homework 2 remain - homework 1 gradient - logaithm
   15. 27 Feature Engineering
   16. 28 Kaggle Task - Creating a baseline - Project 1
   17. 29 ML Big Picture

8. 06 Neural Network for Regression

   5 lessons

   1. 30 Feedforward Neural Network
   2. 31 DP and Multivariate Chain Rule Motivations
   3. 32 NN Big Picture
   4. 33 NN Backpropagation
   5. 34 Backpropagation Homework

9. 07 Data Concepts (Continue)

   5 lessons

   1. 39 Data in Practice - Challenges
   2. 38 Unlimited Challenge - Database - Data in Practice
   3. 37 Augmented - Synthetic - Leakage - Unlimited Variance Challenge
   4. 36 Data-based Challenges - Answers
   5. 35 Data-based Challenges

10. 08 Binary Classification

    7 lessons

    1. 40 Regression - Seperability - Sigmoid - Frame Filter Challenge
    2. 41 Logstic Regrssion - Log Loss Cost function
    3. 42 Confusion Matrix - Preciasion - Recall intro
    4. 43 PR - Fscore - FPR
    5. 44 2 Curves
    6. 45 Average Precision
    7. 46 Imbalanced dataset - fraud project

11. 08 End to End ML

    8 lessons

    1. 47 Requirements and Problem Definition
    2. 48 Requirements Challenge - Brainstorming
    3. 49 Problem Reformulation and Scoping Challenge- Brainstorming
    4. 50 Diagrams - Storage - Developemnt
    5. 51 Development cont - Inference
    6. 52 Inference - Model Deployment
    7. 53 Model Deployment 2
    8. 54 Data Shift - Seniority

12. 09 Multi-class Classification

    4 lessons

    1. 55 Multiclassifier 1
    2. 55 Multiclassifier 2
    3. 56 Model Caliberation
    4. 57 Multiclassifier 2 homworks

13. 10 Unsupervised Learning

    3 lessons

    1. 58 AutoEncoder 1
    2. 59 AutoEncoder 2 - K-means
    3. 60A GMM

14. 11 Misc Topics

    5 lessons

    1. 64 Probabilistic Modeling 4 naive - sampling
    2. 63 Probabilistic Modeling 3
    3. 62 Probabilistic Modeling 2
    4. 61 Probabilistic Modeling 1
    5. 60B KNN - Interview Qs

15. 12 PyTorch Framework

    6 lessons

    1. 65 Deep Learning and Frameworks history
    2. 66 PyTioch Installations
    3. 67 Pytorch intro
    4. 68 PyTorch Continue
    5. 69 PyTorch Continue challenge
    6. 70 Design Challenge Solution

16. 13 CNN

    7 lessons

    1. 71 Comuter Vision Before DNN
    2. 72 Convolutional Operator - pad - stride
    3. 73 Concolutional Layer
    4. 74 Convolutional Network 1
    5. 75 Convolutional Network 2
    6. 76 Misc Topics 1
    7. 77 Misc Topics 2

17. 14 RNN

    6 lessons

    1. 78 RNN 1
    2. 79 RNN 2
    3. 83 LSTM 2
    4. 82 LSTM 1
    5. 81 RNN 4
    6. 80 RNN 3

18. 15 Deep Learning Project

    1 lesson

    1. 84 Deep Learning Project - CVPR 16