Pebellslearn by building
RoadmapMatrixCatalogSandboxSign in

Machine Learning

Outline

38 topics and 112 subtopics mapped. This is the ground the track will cover — the lessons aren't written yet.

  1. 01

    Introduction

    3 subtopics
    • ML Engineer vs AI Engineer
    • Skills and Responsibilities
    • What is an ML Engineer?
  2. 02

    Linear Algebra

  3. 03

    Calculus

    8 subtopics
    • Chain rule of derivation
    • Gradient, Jacobian, Hessian
    • Derivatives, Partial Derivatives
    • Scalars, Vectors, Tensors
    • Singular Value Decomposition
    • Matrix & Matrix Operations
    • Eigenvalues, Diagonalization
    • Determinants, inverse of Matrix
  4. 04

    Statistics

    8 subtopics
    • Basics of Probability
    • Descriptive Statistics
    • Basic concepts
    • Types of Distribution
    • Random Variances, PDFs
    • Bayes Theorem
    • Inferential Statistics
    • Graphs & Charts
  5. 05

    Linear Algebra

  6. 06

    Discrete Mathematics

  7. 07

    Python

  8. 08

    Basic Syntax

    6 subtopics
    • Variables and Data Types
    • Conditionals
    • Data Structures
    • Exceptions
    • Functions, Builtin Functions
    • Loops
  9. 09

    Object Oriented Programming

  10. 10

    Essential libraries

    4 subtopics
    • Numpy
    • Pandas
    • Matplotlib
    • Seaborn
  11. 11

    Data Sources

    5 subtopics
    • Databases (SQL, No-SQL)
    • Internet
    • APIs
    • Mobile Apps
    • IoT
  12. 12

    Data Formats

    5 subtopics
    • JSON
    • Parquet
    • CSV
    • Excel
    • Other Data Formats
  13. 13

    Preprocessing Techniques

    5 subtopics
    • Data Cleaning
    • Dimensionality Reduction
    • Feature Engineering
    • Feature Selection
    • Feature Scaling & Normalization
  14. 14

    Types of Machine Learning

    5 subtopics
    • Unsupervised Learning
    • Semi-supervised Learning
    • Supervised Learning
    • Reinforcement Learning
    • Self-supervised Learning
  15. 15

    What is Machine Learning?

  16. 16

    What is Supervised Learning?

  17. 17

    Classification

    5 subtopics
    • Logistic Regression
    • Support Vector Machines
    • K-Nearest Neighbors (KNN)
    • Gradient Boosting Machines
    • Decision Trees, Random Forest
  18. 18

    Regression

    2 subtopics
    • Linear Regression
    • Polynomial Regression
  19. 19

    What is Unsupervised Learning?

  20. 20

    Clustering

  21. 21

    Dimensionality Reduction

    6 subtopics
    • Overlapping
    • Hierarchical
    • Exclusive
    • Probabilistic
    • Autoencoders
    • Principal Component Analysis
  22. 22

    What is Reinforcement Learning?

    4 subtopics
    • Policy Gradient
    • Actor-Critic Methods
    • Deep-Q Networks
    • Q-Learning
  23. 23

    What is Model Evaluation?

  24. 24

    Metrics to Evaluate

    11 subtopics
    • Accuracy
    • Precision
    • Recall
    • F1-Score
    • ROC-AUC
    • Log Loss
    • Confusion Matrix
    • Forward propagation
    • Back Propagation
    • Perceptron, Multi-layer Perceptrons
    • Activation Functions
  25. 25

    Neural Network (NN) Basics

    1 subtopic
    • Loss Functions
  26. 26

    Scikit-learn

    2 subtopics
    • Ridge
    • Lasso
  27. 27

    Validation Techniques

    2 subtopics
    • LOOCV
    • K-Fold Cross Validation
  28. 28

    Deep Learning Architectures

  29. 29

    Convolutional Neural Network

    4 subtopics
    • Pooling
    • Padding
    • Convolution
    • Strides
  30. 30

    Applications of CNNs

    4 subtopics
    • Image Classification
    • Image Segmentation
    • Image & Video Recognition
    • Recommendation Systems
  31. 31

    Recurrent Neural Networks

    3 subtopics
    • RNN
    • GRU
    • LSTM
  32. 32

    Attention Mechanisms

  33. 33

    Autoencoders

    3 subtopics
    • Transformers
    • Multi-head Attention
    • Self-Attention
  34. 34

    Generative Adversarial Networks

  35. 35

    Natural Language Processing

    5 subtopics
    • Tokenization
    • Lemmatization
    • Stemming
    • Embeddings
    • Attention Models
  36. 36

    Explainable AI

    6 subtopics
    • Train - Test Data
    • Data Preparation
    • Data Loading
    • Tuning
    • Prediction
    • Model Selection
  37. 37

    Deep Learning Libraries

    5 subtopics
    • TensorFlow
    • Keras
    • PyTorch
    • Scikit-learn
    • ElasticNet Regularization
  38. 38

    Why is it important?