Machine learning methods are commonly used across engineering and sciences, from computer systems to physics. Moreover, commercial sites such as search engines, recommender systems (e.g., Netflix, Amazon), advertisers, and financial institutions employ machine learning algorithms for content recommendation, predicting customer behavior, compliance, or risk.
As a discipline, machine learning tries to design and understand computer programs that learn from experience for the purpose of prediction or control.
In this course, you will learn about principles and algorithms for turning training data into effective automated predictions. We will cover:
- Representation, over-fitting, regularization, generalization, VC dimension;
- Clustering, classification, recommender problems, probabilistic modeling, reinforcement learning;
- On-line algorithms, support vector machines, and neural networks/deep learning.
You will be able to:
- Understand principles behind machine learning problems such as classification, regression, clustering, and reinforcement learning
- Implement and analyze models such as linear models, kernel machines, neural networks, and graphical models
- Choose suitable models for different applications
- Implement and organize machine learning projects, from training, validation, parameter tuning, to feature engineering
You will implement and experiment with the algorithms in several Python projects designed for different practical applications.
Your overall score in this class will be a weighted average of your scores for the different components, with the following weights:
- 16% for the lecture exercises (divided equally among the 16 out of 19 lectures)
- 1% for the Homework 0
- 2% for the Project 0
- 12% for the homeworks (divided equally among 4 (out of 5) homeworks)
- 36% for the Projects (divided equally among 4 (out of 5)
- 13% for the Midterm exam (timed)
- 20% for the final exam (timed)
To earn a verified certificate for this course, you will need to obtain an overall score of 60% or more of the maximum possible overall score.
Lecture Exercises, Problem Sets, and Projects
-
The lowest 3 scores among the 19 lectures will be dropped, so only 16 out of 19 lectures will count .
-
The lowest 1 scores among the 5 homeworks (excluding homework 0) will be dropped, so only 4 out of 5 homeworks will count .
-
The lowest 1 score among the 5 projects (excluding project 0) will be dropped, so only 4 out of 5 projects will count .
This policy is to accommodate for scheduling conflict, illness, or events which might deter you from completing the work before the deadline with the best grades you can. However, we still fully expect you to learn the material for any dropped assignments, and the exams will cover everything.
Note that not every homework, set of lecture exercises, project will have the same number of raw points. For example, homework 0 may have 53 points and homework 1 may have 43 points. However, each homework receives the same weight for the purpose of calculating your overall score. Similar for lecture exercises and projects.
Under the “Progress" tab at the top, you can see your score broken down for each assignment, as well as a summary plot.
Timed Exams
The midterm exam and final exam are timed exams . This means that each exam is available for approximately a week, but once you open the exam, there is a limited amount of time (48 hours), counting from when you start, within which you must complete the exam. Please plan in advance for the exams. If you do not complete the whole exam during the allowed time, you will miss the points associated with the questions that have not been answered. The exams are designed to assess your knowledge. There are no extensions granted to these deadlines. You can find the exam dates on the calendar on the previous page.
Warning: Note that the timed exams CANNOT be completed using the edX mobile app.
Exam Access: Note that the midterm and final exams will not be available to audit learners. These exams are assessment for learners interested in the course certificates.
MITx Commitment to Accessibility
If you have a disability-related request regarding accessing an MITx course, including exams, please contact the course team as early in the course as possible (at least 2 weeks in advance of exams opening) to allow us time to respond in advance of course deadlines. Requests are reviewed via an interactive process to meet accessibility requirements for learners with disabilities and uphold the academic integrity for MITx.