Curriculum
(Pre-requisites - ML - Level1
Upon successful completion, student will be promoted to project development
Lesson 1: Introduction to Machine Learning
ï‚· Introduction to Data and Machine Learning
Lesson 2: Walking with Python
ï‚· Understanding Python
Lesson 3: Machine Learning Techniques
ï‚· Types of Learning
 Supervised Learning
 Unsupervised Learning
ï‚· Advice for Applying Machine Learning
ï‚· Machine Learning System Design
Lesson 4: Supervised Learning
ï‚· Regression
ï‚· Classification
Lesson 5: Supervised Learning - Regression
ï‚· Predicting house prices: A case study in Regression
 Linear Regression & Logistic: A Model-Based Approach
 Regression fundamentals: Data and Models
Lesson 6: Supervised Learning - Classification
ï‚· Analyzing the sentiment of reviews: A case study in Classification
 Classification fundamentals : Data and Models
 Understanding Decision Trees and Naive Bayes
 Feature selection in Model building
 Linear classifiers
 Decision boundaries
 Training and evaluating a classifier
 False positives, false negatives, and confusion matrices
 Classification ML block diagram
Lesson 7: Unsupervised Learning
ï‚· Clustering
ï‚· Recommendation
ï‚· Deep Learning
Lesson 8: Unsupervised Learning - Clustering
ï‚· Document retrieval: A case study in clustering and measuring similarity
 Clustering System Overview
 Clustering fundamentals : Data and Models
 Feature selection in Model building
 Prioritizing important words with tf-idf
 Clustering and similarity ML block diagram
Lesson 9: Unsupervised Learning - Recommendation
ï‚· Recommending Products
 Recommender systems overview
 Collaborative filtering
 Understanding Collaborative Filtering and Support Vector Machine
 Effect of popular items
 Normalizing co-occurrence matrices and leveraging purchase histories
 The matrix completion task
 Recommendations from known user/item features
 Recommender systems ML block diagram
Lesson 10: Unsupervised Learning – Deep Learning
ï‚· Deep Learning: Searching for Images
 Searching for images: A case study in deep learning
 Learning very non-linear features with neural networks
 Application of deep learning to computer vision
 Deep learning performance
 Demo of deep learning model on ImageNet data
 Deep learning ML block diagram
Advanced
machine learning
Empowering Kids with simple instructions
Course features:
1. Course instructions
2. Assignments every week
​