Fall 2022 - STAT 440 E100
Learning from Big Data (3)
Class Number: 4668
Delivery Method: In Person
Course Times + Location:
Mo 4:30 PM – 5:20 PM
BLU 10921, Burnaby
We 4:30 PM – 6:20 PM
WMC 2532, Burnaby
Prerequisites:90 units including STAT 350 with a minimum grade of C- and one of STAT 341, STAT 260, or CMPT 225, with a minimum grade of C-, or instructor approval. STAT 240 is also recommended.
A data-first discovery of advanced statistical methods. Focus will be on a series of forecasting and prediction competitions, each based on a large real-world dataset. Additionally, practical tools for statistical modeling in real-world environments will be explored.
STAT 440 is suitable for senior students who have a minimum of 90 units.
A mixed lecture and seminar-based course to introduce Statistics graduate students to theory, models and methods in Genetics and Genomics. Topics include genome-wide association study, the ancestral recombination graph, population genetics, differential privacy, whole genome sequencing, computational molecular genetics, evolution and selection, phenotype prediction.
The course will be split into several modules. Each module will focus on a particular dataset. At the start of each module, students will be randomly divided into teams. A subset of the dataset will be given to all teams (the training data) and the rest of the dataset will be withheld (the test data). Students will learn modern machine learning methods for predicting aspects of the test data based on the training data. This test/train paradigm is often encountered in both academic and industrial settings. The methods will include bagging, boosting, deep learning, model blending and cross-validation. The students will learn how to implement these methods using standard software packages such as scikit-learn and tensorflow.They will use these methods (and any other techniques they wish) to predict aspects of the test data. During each module, teams will submit their predictions and see the results of those predictions on the withheld test data. Marks for competition results will be awarded based on the accuracy of their predictions.
- Assignments 10%
- Competitions 50%
- Presentations 20%
- Exam 20%
Assignments and Grading Procedures
- Assignments (10%): Problem sets will be assigned following the methods taught in the lectures.
- Competitions (50%): Two or three datasets will be assigned as competitions, to be done individually or in small groups. Marks for predictions of held-out target variables will be awarded based on performance relative to classmates and objective baselines.
- Presentations (20%): Students will prepare slides and talks covering recent methodology and advances in statistics and machine learning.
- Exams (20%): Short in-class exams will be given, covering theory.
Above Grading is subject to change.
Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (A. Géron, 2017, O'Reilly)
Deep Learning (I. Goodfellow and Y. Bengio and A. Courville, 2016, MIT Press)
Machine Learning: A Probabilistic Perspective (K.P. Murphy, 2012, MIT Press);
Introduction to Machine Learning with Python (A. Müller and S. Guido, 2016, O'Reilly)
Linear Algebra, 5th Edition (S. Friedberg, A. Insel and L. Spence, 2018, Pearson)
Learning R (R. Cotton, 2013, O'Reilly)
Information Theory, Inference, and Learning Algorithms (D. MacKay, 2003, Cambridge University Press)
Elements of Statistical Learning (T. Hastie, R. Tibshirani and J. Friedman, 2009, Springer)
Department Undergraduate Notes:
Students with Disabilities:
Students requiring accommodations as a result of disability must contact the Centre for Accessible Learning 778-782-3112 or email@example.com.
Students looking for a tutor should visit https://www.sfu.ca/stat-actsci/all-students/other-resources/tutoring.html. We accept no responsibility for the consequences of any actions taken related to tutors.
ACADEMIC INTEGRITY: YOUR WORK, YOUR SUCCESS
SFU’s Academic Integrity website http://www.sfu.ca/students/academicintegrity.html is filled with information on what is meant by academic dishonesty, where you can find resources to help with your studies and the consequences of cheating. Check out the site for more information and videos that help explain the issues in plain English.
Each student is responsible for his or her conduct as it affects the university community. Academic dishonesty, in whatever form, is ultimately destructive of the values of the university. Furthermore, it is unfair and discouraging to the majority of students who pursue their studies honestly. Scholarly integrity is required of all members of the university. http://www.sfu.ca/policies/gazette/student/s10-01.html
Required Reading Notes:
Course Materials, including digital textbooks, are available through the SFU Bookstore by simply searching by your Campus/Term/Class at https://shop.sfu.ca/Course/campus.