Skilific

Course Modules

1. Chapter 1
   
   Poglavlje 1
   
   01.1. Neural Networks Intuition

   Lessons 4 Lekcije 4

   1. 1. Welcome

   2. 2. Neurons and the Brain

   3. 3. Demand Prediction

   4. 4. Example Recognizing Images

2. Chapter 2
   
   Poglavlje 2
   
   01.2. Neural Network Model

   Lessons 3 Lekcije 3

   1. 1. Neural Network Layer

   2. 2. More Complex Neural Networks

   3. 3. Inference Making Predictions Forward Propagation

3. Chapter 3
   
   Poglavlje 3
   
   01.3. Tensorflow Implementation

   Lessons 3 Lekcije 3

   1. 1. Inference in Code

   2. 2. Data in Tensorflow

   3. 3. Building a Neural Network

4. Chapter 4
   
   Poglavlje 4
   
   01.4. Neural Network Implementation in Python

   Lessons 2 Lekcije 2

   1. 1. Forward Prop in a Single Layer

   2. 2. General Implementation of Forward Propagation

5. Chapter 5
   
   Poglavlje 5
   
   01.5. Speculations on Artificial General Intelligence AGI

   Lessons 1 Lekcije 1

   1. 1. Is There a Path to AGI

6. Chapter 6
   
   Poglavlje 6
   
   01.6. Vectorization (Optional)

   Lessons 4 Lekcije 4

   1. 1. How Neural Nnetworks are Implemented Efficiently

   2. 2. Matrix Multiplication

   3. 3. Matrix Multiplication Rules

   4. 4. Matrix Multiplication Code

7. Chapter 7
   
   Poglavlje 7
   
   02.1. Neural Network Training

   Lessons 2 Lekcije 2

   1. 1. Tensorflow Implementation

   2. 2. Training Details

8. Chapter 8
   
   Poglavlje 8
   
   02.2. Activation Functions

   Lessons 3 Lekcije 3

   1. 1. Alternatives to the Sigmoid Activation

   2. 2. Choosing Activation Functions

   3. 3. Why do we Need Activation Functions

9. Chapter 9
   
   Poglavlje 9
   
   02.3. Multiclass Classification

   Lessons 5 Lekcije 5

   1. 1. Multiclass

   2. 2. Softmax

   3. 3. Neural Network with Softmax Output

   4. 4. Improved Implementation of Softmax

   5. 5. Classification with Multiple Outputs (Optional)

10. Chapter 10
    
    Poglavlje 10
    
    02.4. Additional Neural Network Concepts

    Lessons 2 Lekcije 2

    1. 1. Advanced Optimization

    2. 2. Additional Layer Types

11. Chapter 11
    
    Poglavlje 11
    
    02.5. Back Propagation (Optional)

    Lessons 3 Lekcije 3

    1. 1. What is a Derivative

    2. 2. Computation Graph

    3. 3. Larger Neural Network Example

12. Chapter 12
    
    Poglavlje 12
    
    03.1. Advice for Applying Machine Learning

    Lessons 3 Lekcije 3

    1. 1. Deciding What to Try Next

    2. 2. Evaluating a Model

    3. 3. Model Selection and Training Cross Validation Test Sets

13. Chapter 13
    
    Poglavlje 13
    
    03.2. Bias and Variance

    Lessons 6 Lekcije 6

    1. 1. Diagnosing Bias and Variance

    2. 2. Regularization and Bias Variance

    3. 3. Establishing a Baseline Level of Performance

    4. 4. Learning Curves

    5. 5. Deciding What to Try Next Revisited

    6. 6. Bias Variance and Neural Networks

14. Chapter 14
    
    Poglavlje 14
    
    03.3. Machine Learning Development Process

    Lessons 6 Lekcije 6

    1. 1. Iterative Loop of ML Development

    2. 2. Error Analysis

    3. 3. Adding Data

    4. 4. Transfer Learning Using Data from a Different Task

    5. 5. Full Cycle of a Machine Learning Project

    6. 6. Fairness Bias and Ethics

15. Chapter 15
    
    Poglavlje 15
    
    03.4. Skewed Datasets (Optional)

    Lessons 2 Lekcije 2

    1. 1. Error Metrics for Skewed datasets

    2. 2. Trading off Precision and Recall

16. Chapter 16
    
    Poglavlje 16
    
    04.1. Decision Trees

    Lessons 2 Lekcije 2

    1. 1. Decision Tree Model

    2. 2. Learning Process

17. Chapter 17
    
    Poglavlje 17
    
    04.2. Decision Tree Learning

    Lessons 6 Lekcije 6

    1. 1. Measuring Purity

    2. 2. Choosing a Split Information Gain

    3. 3. Putting it Together

    4. 4. Using One Hot Encoding of Categorical Features

    5. 5.Continuous Valued Features

    6. 6. Regression Trees Optional

18. Chapter 18
    
    Poglavlje 18
    
    04.3. Tree Ensembles

    Lessons 5 Lekcije 5

    1. 1. Using Multiple Decision Trees

    2. 2. Sampling with Replacement

    3. 3. Random Forest Algorithm

    4. 4. Xgboost

    5. 5. When to Use Decision Trees

19. Chapter 19
    
    Poglavlje 19
    
    04.4. Conversations with Andrew (Optional)

    Lessons 1 Lekcije 1

    1. 1. Andrew NG and Chris Manning on Natural Language Processing

20. Chapter 20
    
    Poglavlje 20
    
    01.1. Overview of Machine Learning

    Lessons 2 Lekcije 2

    1. 1. Welcome to Machine Learning

    2. 2. Applications of Machine Learning

21. Chapter 21
    
    Poglavlje 21
    
    01.2. Supervised VS Unsupervised Machine Learning

    Lessons 6 Lekcije 6

    1. 1. What is Machine Learning

    2. 2. Supervised Learning Part 1

    3. 3. Supervised Learning Part 2

    4. 4. Unsupervised Learning Part 1

    5. 5. Unsupervised Learning Part 2

    6. 6. Jupyter Notebooks

22. Chapter 22
    
    Poglavlje 22
    
    01.3. Regression Model

    Lessons 6 Lekcije 6

    1. 1. Linear Regression Model Part 1

    2. 2. Linear Regression Model Part 2

    3. 3. Cost Function Formula

    4. 4. Cost Function Intuition

    5. 5. Visualizing the Cost Function

    6. 6. Visualization Examples

23. Chapter 23
    
    Poglavlje 23
    
    01.4. Train the Model with Gradient Descent

    Lessons 6 Lekcije 6

    1. 1. Gradient Descent

    2. 2. Implementing Gradient Descent

    3. 3. Gradient Descent Intuition

    4. 4. Learning Rate

    5. 5. Gradient Descent for Linear Regression

    6. 6. Running Gradient Descent

24. Chapter 24
    
    Poglavlje 24
    
    02.1. Multiple Linear Regression

    Lessons 4 Lekcije 4

    1. 1. Multiple Features

    2. 2. Vectorization Part 1

    3. 3. Vectorization Part 2

    4. 4. Gradient Descent for Multiple Linear Regression

25. Chapter 25
    
    Poglavlje 25
    
    02.2. Gradient Descent in Practice

    Lessons 6 Lekcije 6

    1. 1. Feature Scaling Part 1

    2. 2. Feature Scaling Part 2

    3. 3. Checking Gradient Descent for Convergence

    4. 4. Choosing the Learning Rate

    5. 5. Feature Engineering

    6. 6. Polynomial Regression

26. Chapter 26
    
    Poglavlje 26
    
    03.1. Classification with Logistic Regression

    Lessons 3 Lekcije 3

    1. 1. Motivations

    2. 2. Logistic Regression

    3. 3. Decision Boundary

27. Chapter 27
    
    Poglavlje 27
    
    03.2. Cost Function for Logistic Regression

    Lessons 2 Lekcije 2

    1. 1. Cost Function for Logistic Regression

    2. 2. Simplified Cost Function for Logistic Regression

28. Chapter 28
    
    Poglavlje 28
    
    03.3. Gradient Descent for Logistic Regression

    Lessons 1 Lekcije 1

    1. 1. Gradient Descent Implementation

29. Chapter 29
    
    Poglavlje 29
    
    03.4. The Problem of Overfitting

    Lessons 5 Lekcije 5

    1. 1.The Problem of Overfitting

    2. 2. Addressing Overfitting

    3. 3. Cost Function with Regularization

    4. 4. Regularized Linear Regression

    5. 5. Regularized Logistic Regression

30. Chapter 30
    
    Poglavlje 30
    
    03.5. Conversations with Andrew (Optional)

    Lessons 1 Lekcije 1

    1. 1. Andrew NG and Fei Fei Li on Human Centered AI

31. Chapter 31
    
    Poglavlje 31
    
    01.1. Welcome to the Course

    Lessons 1 Lekcije 1

    1. 1. Welcome

32. Chapter 32
    
    Poglavlje 32
    
    01.2. Clustering

    Lessons 6 Lekcije 6

    1. 1. What is Clustering

    2. 2. K Means Intuition

    3. 3. K Means Algorithm

    4. 4. Optimization Objective

    5. 5. Initializing K Means

    6. 6. Choosing the Number of Clusters

33. Chapter 33
    
    Poglavlje 33
    
    01.3. Anomaly Detection

    Lessons 6 Lekcije 6

    1. 1. Finding Unusual Events

    2. 2. Gaussian Normal Distribution

    3. 3. Anomaly Detection Algorithm

    4. 4. Developing and Evaluating an Anomaly Detection System

    5. 5. Anomaly Detection VS Supervised Learning

    6. 6. Choosing what Features to Use

34. Chapter 34
    
    Poglavlje 34
    
    02.1. Collaborative Filtering

    Lessons 4 Lekcije 4

    1. 1. Making Recommendations

    2. 2. Using per Item Features

    3. 3. Collaborative Filtering Algorithm

    4. 4. Binary Labels Favs Likes and Clicks

35. Chapter 35
    
    Poglavlje 35
    
    02.2. Recommender Systems Implementation Detail

    Lessons 3 Lekcije 3

    1. 1. Mean Normalization

    2. 2. Tensorflow Implementation of Collaborative Filtering

    3. 3. Finding Related Items

36. Chapter 36
    
    Poglavlje 36
    
    02.3. Content Based Filtering

    Lessons 5 Lekcije 5

    1. 1. Collaborative Filtering VS Content Based Filtering

    2. 02_deep-learning-for Content Based Filtering

    3. 3. Recommending from a Large Catalogue

    4. 4. Ethical Use of Recommender Systems

    5. 5. Tensorflow Implementation of Content Based Filtering

37. Chapter 37
    
    Poglavlje 37
    
    02.4. Principal Component Analysis

    Lessons 3 Lekcije 3

    1. 1. Reducing the Number of Features (Optional)

    2. 2. PCA Algorithm (Optional)

    3. 3. PCA in Code (Optional)

38. Chapter 38
    
    Poglavlje 38
    
    03.1. Reinforcement Learning Introduction

    Lessons 5 Lekcije 5

    1. 1. What is Reinforcement Learning

    2. 2. Mars Rover Example

    3. 3. The Return in Reinforcement Learning

    4. 4. Making Decisions Policies in Reinforcement Learning

    5. 5. Review of Key Concepts

39. Chapter 39
    
    Poglavlje 39
    
    03.2. State Action Value Function

    Lessons 4 Lekcije 4

    1. 1. State Action Value Function Definition

    2. 2. State Action Value Function Example

    3. 3. Bellman Equation

    4. 4. Random Stochastic Environment (Optional)

40. Chapter 40
    
    Poglavlje 40
    
    03.3. Continuous State Spaces

    Lessons 7 Lekcije 7

    1. 1. Example of continuous state Space Applications

    2. 2. Lunar Lander

    3. 3. Learning the State Value Function

    4. 4. Algorithm Refinement Improved Neural Network Architecture

    5. 5. Algorithm Refinement Greedy Policy

    6. 6. Algorithm Refinement Mini Batch and Soft Updates (Optional)

    7. 07_the-state-of-reinforcement-learning

41. Chapter 41
    
    Poglavlje 41
    
    03.4. Summary and Thank You

    Lessons 1 Lekcije 1

    1. 1. Summary and Thank You

42. Chapter 42
    
    Poglavlje 42
    
    03.5. Conversations with Andrew (Optional)

    Lessons 1 Lekcije 1

    1. 1.Andrew NG and Chelsea Finn on AI and Robotics