0% found this document useful (0 votes)
73 views23 pages

Course Logistics and Introduction: CSN-526 Machine Learning

This document provides an overview and logistics for a machine learning course. It outlines that there will be three weekly lectures on Microsoft Teams, course material will be posted online, and announcements will be sent via email. Grading will be based on a midterm, final exam, and course project done in groups of five students. The course aims to introduce foundational machine learning models and algorithms and help students apply them and evaluate models for different problems.

Uploaded by

ssss
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
73 views23 pages

Course Logistics and Introduction: CSN-526 Machine Learning

This document provides an overview and logistics for a machine learning course. It outlines that there will be three weekly lectures on Microsoft Teams, course material will be posted online, and announcements will be sent via email. Grading will be based on a midterm, final exam, and course project done in groups of five students. The course aims to introduce foundational machine learning models and algorithms and help students apply them and evaluate models for different problems.

Uploaded by

ssss
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 23

Course Logistics and Introduction

CSN-526
Machine Learning
2
Course Logistics
▪ Course Name: Machine Learning (CSN-526)
▪ An introductory course – supposed to be your first intro to the subject

▪ Three lectures every week on Microsoft Team

▪ All material will be posted on Microsoft Team for the course

▪ Course-related announcements will be sent on the class mailing list (and also on
Microsoft Teams)

▪ Timings:
Lectures: Monday (02:00 - 02:55), Tuesday (02:00 - 02:55), Thursday (02:00 - 02:55)
Tutorials: Wednesday (04:05-05:00), Wednesday (05:05 - 06:00)
3
Grading

▪ Mid-term Exam: 25%

▪ End-term Exam: 50%

▪ Course Project: 25%


4
Course Project: 25%
• Project to be done in groups of five (5) students each
• Start forming your group from today onwards
• Will ask you to submit group details after 1-2 weeks
• Groups can only contain registered students (no auditors)
• You may propose your own project idea
• but please discuss the scope/feasibility with TAs
• Many types of projects possible (theoretical/applied/mixed); even building a
cool/useful app/portal for something using ML as its backend would be a nice
project. Explore around for ideas.
• Important: Don’t (re)use a project from another course you’ve done before (or
doing currently)
• Need to submit a formal project proposal
• Should contain a problem description, tentative plan of action, etc (I’ll provide more guidelines
later)
5
Course Project: 25%
• Multiple Project presentations to assess the progress of the project
• Project evaluation will be done based on the novelty and new ideas of
the work
• Final Submission will include code + report
• Code should be in Python – start learning Python today
• Report must be in LaTeX – start learning LaTeX today
• Python Resources: several available –choose your favourite
• www.geeksforgeeks.org/python-programming-language/
• LaTeX resources: several available –choose your favourite
• www.overleaf.com/learn/latex/Tutorials
6
Textbook and References
▪ Many excellent texts but none “required”. Some include:

▪ Different books might vary in terms of


▪ Set of topics covered
▪ Flavor (e.g., classical statistics, deep learning, probabilistic/Bayesian, theory)
▪ Terminology and notation (beware of this especially)
▪ We will provide you the reading material from the relevant sources
▪ Avoid using too many sources until you have developed a reasonable
understanding of a concept
7
Textbook and References
• Hal Daumé III, A Course in Machine Learning (CIML), 2017 (freely available online)
• Kevin Murphy, Machine Learning: A Probabilistic Perspective (MLAPP), MIT Press,
2012
• Christopher Bishop, Pattern Recognition and Machine Learning (PRML), Springer,
2007.
• David G. Stork, Peter E. Hart, and Richard O. Duda. Pattern Classification (PC), Wiley-
Blackwell, 2000
• Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning (DL), MIT
Pess, 2016 (individual chapters freely available online)
• Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical
Learning (ESL), Springer, 2009 (freely available online)
• Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From
Theory to Algorithms (UML), Cambridge University Press, 2014
• Mehryar Mohri, Afshin Rostamizadeh and Ameet Talwalkar. Foundations of Machine
Learning (FOML), MIT Press, 2012
8
Textbook and References
▪ Some of the course materials have been taken from the following links:

▪ https://www.cse.iitk.ac.in/users/piyush/courses/ml_autumn18/index.html

▪ https://github.com/purushottamkar/ml19-20w

▪ Thanks to Prof. Piyush for supporting in preparing the course material


9
Course Goals..
▪ Introduction to the foundations of machine learning models and algos

▪ Focus on developing the ability to


▪ Understand the underlying principles behind ML models and algos
▪ Understand how to implement and evaluate them
▪ Understand/develop intuition on choosing the right ML model/algo for your problem

▪ (Hopefully) inspire you to work on and learn more about ML

▪ Not an introduction to popular software frameworks and libraries, such as


scikit-learn, PyTorch, Tensorflow, etc
▪ Can explore once you have some understanding of various ML techniques
Introduction to Machine Learning
11
Machine Learning (ML)
▪ Designing algorithms that ingest data and learn a model of the data
▪ The learned model can be used to
▪ Detect patterns/structures/themes/trends etc. in the data
▪ Make predictions about future data and make decisions

▪ Modern ML algorithms are heavily “data-driven”


▪ No need to pre-define and hard-code all the rules (infeasible/impossible anyway)
▪ The rules are not “static”; can adapt as the ML algo ingests more and more data
12
ML: From What It Does to How It Does It?
▪ ML enables intelligent systems to be data-driven rather than rule-driven
▪ How: By supplying training data and building statistical models of data
▪ Pictorial illustration of an ML model for binary classification:

A Linear Classifier (the statistical model)


13
ML: From What It Does to How It Does It?
▪ ML enables intelligent systems to be data-driven rather than rule-driven
▪ How: By supplying training data and building statistical models of data
▪ Pictorial illustration of an ML model for binary classification:

A Probabilistic Classifier (the statistical model)

P(“cat”|image) P(“dog”|image)
14
Overfitting = Bad ML
▪ Doing perfectly on training data is not good enough

▪ A good ML model must generalize well on unseen (test data)

▪ Simpler models should be preferred over more complex ones!


15
ML Applications Abound..

Picture courtesy: gizmodo.com,rcdronearena.com,www.wiseyak.com,www.charlesdong.com


16
Key Enablers for Modern ML
▪ Availability of large amounts of data to train ML models

▪ Increased computing power (e.g., GPUs)


17
ML: Some Success Stories
18
ML: Some Success Stories
19
ML: Some Success Stories

Picture courtesy: https://news.microsoft.com/


20
ML: Some Success Stories
▪ Automatic Program Correction

Example from “Compilation error repair: for the student programs, from the student programs”, Ahmed et al (2018)
21
Good ML Systems Should be Fair and Unbiased
▪ Good ML should not just be about getting high accuracies

▪ Should also ensure that the ML models are fair and unbiased
Criminals?

Not Criminals?

An image captioning Don’t want a self-driving car Don’t want a predictive policing
system should not always that is more likely to hit black system that predicts criminality
assume a specific gender in people than white people using facial features
examples like the above

▪ A lot of recent focus on Fairness and Transparency of ML systems


Picture courtesy: Bhargava and Forsyth (2019), https://www.thestranger.com/, Xiaolin Wu and Xi Zhang, “Automated Inference on Criminality Using Face Images”
22
Machine Learning Tools
▪ Scikit-Learn
▪ Pytorch
▪ Google Colab
▪ Jupyter Notebook
▪ Tensorflow
▪ Google Cloud AutoML
▪ Numpy
▪ MatPlotLib
▪ Open CV
▪ Microsoft Azure Machine Learning
▪ Amazon Machine Learning
23
Next Class
▪ Various Flavors of ML problems

▪ Data and features

▪ Basic mathematical operations on data and features

You might also like