Download Copy of Machine Learning and Data Science Syllabus(75 hours)

Pawan Niroula
Machine Learning and Data Science - Syllabus
Machine Learning
Review of Python Programming - 2 hours
1. Python List, Dictionary with comprehensions
2. Debugging in Python.
3. Object Oriented Programming Paradigm with Python
Introduction to Machine Learning - 2 hours
1.
2.
3.
4.
5.
6.
Machine learning and its need.
Recent development in Machine Learning.
Types of Machine Learning Systems.
Challenges in Machine Learning.
Machine Learning workflow.
Basic Introduction to Neural Networks.
Introduction to Python Packages and Dependency Management- 1 hour
1. Introduction to Python Package Index (PyPI).
2. Introduction to conda and pip for dependency management.
Setting up the ML-Environment - 2 hours
1. Setting up the IDE
2. Introduction to Jupyter Notebook and Google Collab.
3. Review Git.
Introduction to Machine Learning Libraries - 2 hours
1.
2.
3.
4.
5.
Numpy
Pandas
Matplotlib/Plotly
Scikit Learn
NLTK
Pawan Niroula
Machine Learning Model Evaluation Metrics - 2 hours
1.
2.
3.
4.
5.
Introduction to machine learning models.
Measuring accuracy of a model.
Introduction to Precision/Recall.
Confusion Matrix and relation with Precision and Recall.
Introduction to Bias and Variance.
Supervised Machine Learning Algorithms - 10 days
1.
2.
3.
4.
5.
Introduction to supervised approach.
Linear Regression
Logistic Regression.
K-Nearest Neighbors.
Decision Trees.
Unsupervised Machine Learning Algorithms - 5 days
1. Introduction to Unsupervised approach.
2. Clustering and Associations.
Ensemble Methods and Dimensionality Reduction - 5 days
1.
2.
3.
4.
Introduction to Ensemble Learning Method.
Bagging/Boosting
Introduction to Curse of Dimensionality.
PCA for Dimensionality Reduction.
Deep Learning
Introduction to deep learning, terms and concepts - 3 hours
1.
2.
3.
4.
Concepts on Artificial Neural Networks.
Deep Learning and its need.
Introduction to Activation Functions, epochs and iterations.
Applications of Deep Learning.
Pawan Niroula
Training process and related concepts in Deep Learning - 6 hours
1.
2.
3.
4.
5.
6.
Training a Logistic Regression Model.
Introduction to cost function.
Gradient Descent and Backpropagation.
Effect of learning rate and regularization concepts.
Vanishing and Exploding Gradients.
Concepts of overfitting and underfitting.
Introduction to PyTorch, a Deep Learning Framework - 4 hours
1.
2.
3.
4.
Introduction to tensors, dataset and data loaders.
Neural Network architectures with PyTorch.
Optimization of the networks.
Training, saving and loading the PyTorch models.
Computer Vision and Convolutional Neural Networks - 10 hours
1. Introduction and application of Computer Vision.
2. Introduction to Convolutional Neural Networks.
3. Components of Convolutional Neural Networks.
a. Pooling Layers
b. Fully Connected Layers
c. Dropout and Activation Functions
d. Output Layers
4. Mathematics for layers calculation in CNN.
5. Implementation of a CNN in PyTorch for image classification tasks.
Pawan Niroula
Natural Language Processing - 10 hours
1. Concepts on Natural Language Processing.
2. Data Preprocessing steps and pipelines.
a. Tokenization of input text.
b. Stop words Removals.
c. Stemming and Lemmatization.
3. Introduction to Encoder and Decoders.
4. Introduction to LSTMs.
5. Sentiment Analysis with NLP pipelines.
6. Introduction to recent NLP models (Attention models).
Data Science
Introduction to Data Science - 2 hours
1.
2.
3.
4.
Introduction to data and data source.
Project Structure for data science.
Data Preprocessing and feature engineering.
Introduction to data drift and concept drift.
Exploratory Data Analysis - 6 hours
1. Understanding the story behind data.
2. Data Manipulation using Pandas.
3. Data Visualization.
Working with Texts in Python - 8 hours
1.
2.
3.
4.
Introduction to NLP
Introduction to ELK stack.
Handling texts and text analysis.
Basic Introduction to Spacy.