Introducing
Your new presentation assistant.
Refine, enhance, and tailor your content, source relevant images, and edit visuals quicker than ever before.
Trending searches
Introduction to ML
32
ML
I n t r o d u c t i o n t o
Instructor: Zahraa Zakariya Saleh
Course
Overview
This class is an introductory undergraduate course in machine learning. The class will briefly cover topics in regression, classification, mixture models, neural networks, deep learning and reinforcement learning
Course overview
Prerequisites: You should understand basic probability and statistics, and college-level algebra and calculus. For example it is expected that you know about standard probability distributions (Gaussians), and also how to calculate derivatives. Knowledge of linear algebra is also expected, and knowledge of mathematics underlying probability models will be useful. For the programming assignments, you should have some background in programming, and it would be helpful if you know Python.
TextBook
TextBook
of ML
Required
Recommended
Ethem Alpaydin, Introduction to Machine Learning, Second Edition, http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=12012. This book will
cover all the material in the course.
- Stephen Marsland, Machine Learning: An Algorithmic Perspective. http://www.amazon.com/Machine-Learning-Algorithmic-PerspectiveRecognition/dp/1420067184 .
- Christopher M. Bishop, Pattern Recognition and Machine Learning. http://research.microsoft.com/en-us/um/people/cmbishop/prml/.
- Tom Mitchell, Machine Learning, http://www.cs.cmu.edu/~tom/mlbook.html.
Course Schedule
Course Schedule
Course Schedule
Week1
- Class overview: Class organization, topics overview, software etc.
- Introduction: what is ML; Problems, data, and tools; Visualization; Matlab
Week2
- Linear regression; SSE; gradient descent; closed form; normal equations; features
Week3
- Classification problems; decision boundaries; nearest neighbor methods
Week4
- Linear classifiers
Week5
- Overfitting and complexity; training, validation, test data, and introduction to Matlab (II)
Week6
- Logistic regression, online gradient descent, Neural Networks
- Review for Mid-term
- Mid-term
Course Schedule
Week7
Week8
- Decision tree
- Ensemble methods: Bagging, random forests, boosting
Week9
Week10
- Unsupervised learning: clustering, k-means, hierarchical agglomeration
- Advanced discussion on clustering
Week11
Week12
- support vector machines (SVM)
Week13
- Reinforcement Learning
Week14
- Review for Final exam
- Final exam
Week15
Learning Outcome
Outcome
Learning
Outcome Learning
Develop an appreciation for what is involved in learning models from data.
Understand a wide variety of learning algorithms
Understand how to evaluate models generated from data
Apply the algorithms to a real-world problem
Machine Learning Resources
ML Resources
Step 4
Edmodo
Introduction
AI vs ML
Artificial Intelligence
AI a broad term that refers to computers thinking more like humans.
AI is a neural net which was inspired by the structure of the human brain
AI
- Weak AI
- General AI
- Strong AI
Human vs AI
Computer vision
Anomaly detection
Categorization
Voice-to-text
Application
Audio generation
APPLICATIONS
Recommendation engine
Image generation
Natural Language Querying (NLQ)
Natural Language Processing (NLP)
Natural Language Generation (NLG)
Natural Language Understanding (NLU)
ML a subcategory of artificial intelligence that involves learning from data without being explicitly programmed.
ML
- Algorithm is set of rules to be followed when solving problems.
- Algorithm in ML take in data and perform calculation to find an answer.
Algorithm
Today, ML algorithms enable computers to communicate with human, predict natural disaster, drive cars
- The efficiency and accuracy of the algorithms are dependent on how well the algorithm was trained
Unsupervised
machine learning algorithms
- provides unlabeled data that the algorithm tries to make sense of by extracting features and patterns on its own.
- can be further grouped into clustering and association problems.
The algorithm learns on a labeled dataset, providing an answer key that the algorithm can use to evaluate its accuracy on training data
ML Algorithms Types
Supervised
machine learning algorithms
Machine Learning Applications
Application
AI development of intelligent machines that act like human.
ML is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes over time, without being explicitly programmed to do.
AI types consist of Weak AI, General AI, Super AI
ML types consist of supervised and unsupervised