705.601.81 - Applied Machine Learning

Course Structure

The course materials are divided into modules, one for each week of the course. All course materials and assignments will be housed in Canvas and Microsoft Teams. The module content can be accessed by clicking Modules in the Canvas menu. A module will have several sections including the overview, content, readings, discussions, and assignments. You are encouraged to preview all sections of the module before starting. Most modules run for a period of seven (7) days, exceptions are noted in the Course Outline. You should regularly check the Calendar and Announcements for assignment due dates.

Course Topics

• Application of Machine Learning in Computer Vision
• Data Features
• Preprocessing Datasets for Machine Learning
• Model Evaluation
• Supervised Learning
• Ensemble Learning
• Regression
• Unsupervised Learning
• Reinforcement Learning
• Apriori Analysis
• Multilayer Perceptron (Neural Network)
• Model Regularization
• Introduction to PyTorch
• Introduction to TensorFlow

Course Goals

By the end of the course, you will be able to:

• Explain major stages of a machine learning pipeline: Preprocessing, model development, and evaluation.
• Pre-process and explore data at hand for model development.
• Describe supervised, unsupervised, reinforcement, and ensemble learning concepts.
• Describe probabilistic and distance-based ML algorithms.
• Using online data sources and example real-world problems, compare, contrast and utilize major algorithms - Naive Bayes, SVM, Random Forest, Deep Learning Neural Networks.
• Develop and implement basic ML stages in Anaconda Python software environment.
• Evaluate the developed model for performance, speed, deployment and avoiding model over-fit.
• Familiarize with PyTorch and TensorFlow neural network frameworks.

Course Learning Outcomes (CLOs)

• Apply programming languages to solve data science problems, specifically Python
• Apply machine learning to data science problems, specifically ML pipelines
• Familiarize mathematical concepts that support ML methods
• Effectively communicate key elements of the data science process, specifically ML pipelines
• Recognize professional responsibilities and make informed judgments in practicing data science

Textbooks

Raschka, S., & Mirjalili, V. (2019). Python machine learning (3rd ed). Birmingham, UK: Packt Publishing Ltd. ISBN-13: 978-1789955750.

Textbook information for this course is available online through the appropriate bookstore website: For online courses, search the MBS website. 

Required Software

Jupyter Notebook

This course will use Python as its programming language, which is deemed as the number 1 data science programming language (reference: online resources). This course will also use Jupyter Notebook which is a document that contains both code and rich text elements, such as figures, links, and equations. A Jupyter notebook about the Jupyter Notebook itself is provided in the first module. This notebook contains how to install the Anaconda Python development environment that will be used in this course.

Student Coursework Requirements

It is expected that each module will take approximately 8–15 hours per week to complete. Here is an approximate breakdown:

• Reading the assigned sections of the texts, some outside reading (approximately 1–2 hours per week).
• Listening and watching to the audio annotated slide presentations (approximately 1 hour per week).
• Following and re-running the Jupyter notebook slides (approximately 1–2 hour per week).
• Participating in discussions (approximately 1–2 hour per week).
• Completing assignments (approximately 4–8 hours per week).

This course will consist of the following basic student requirements:

Discussions (25% of Final Grade Calculation)

An important part of your course grade is participating in Discussions with your classmates. Discussions will be held over the course of two weeks and will be conducted in Microsoft Teams, with a separate channel for each Discussion.

Post your initial response to the discussion questions by the evening of Day 7 for the first week of the Discussion (Modules 1, 3, 5, 7, 9, 11, and 13). Posting a response to the discussion question is part one of your grade for module discussions (i.e., Timeliness).

Part two of your grade for module discussion is your interaction (i.e., responding to classmate postings with thoughtful responses) with your classmates (i.e., Critical Thinking). This should be completed by the evening of Day 7 for the second week of the Discussion (Modules 2, 4, 6, 8, 10, 12, and 14). Just posting your response to a discussion question is not sufficient; I want you to interact with your classmates. Be detailed in your postings and in your responses to your classmates' postings. Feel free to agree or disagree with your classmates. Please ensure that your postings are civil and constructive.

In addition, you should ask questions and answer your classmates’ questions as part of the Discussion grade. Asking questions is one of the best ways to better understand the course content. I will do my best to answer the questions you post, but your classmates may be able to give you an answer more quickly than I can!

I will monitor module discussions and will respond to some of the discussions as discussions are posted. In some instances, I will summarize the overall discussions and post the summary for the module.

Discussions are evaluated by the following grading elements (please check the Discussion Rubric):

1. Timeliness (30%)
2. Cross-Section of Posting (30%)
3. Critical Thinking, Relevance (40%)

Quizzes (15% of Final Grade Calculation)

Quizzes encourage the student to watch the module videos and follow the Jupyter notebooks in their studying and learning activities. There might be questions which may look irrelevant but these have to be taken with the intent of measuring the amount of attention student pays to the course materials. Students who watch the videos should be able to achieve full score easily.

Assignments (60% of Final Grade Calculation)

Assignments will include real-world problems. Although the Assignments will usually reflect the current material, I will also give on occasion a brain-building problem that may no direct relation to the material but rather may require basic logical reasoning to solve.

Assignments are assigned more-or-less every week and can involve basic materials, further examination of concepts introduced and presented in class and in the textbook, brainteasers, and more challenging questions problems. Problems will be the basis for class discussions as well; be prepared to ask and answer questions and discuss the problems.

Any course materials prepared for evaluation for grades must be turned in Canvas in .ipynb format (Jupyter Notebooks). All assignments are due according to the dates in the Calendar. If there is a legitimate reason why an assignment is going to be late and this can be known in advance (i.e., excluding illness) then the instructor must be notified of such. Illness is a legitimate excuse for lateness but please let me know as soon as possible and we can make arrangements for delivery.

NO ASSIGNMENTS WILL BE ACCEPTED IF SUCH NOTIFICATION WAS NOT MADE.

Assignment Guidelines

The course goal is introducing machine learning pipeline design and analysis as a branch of study in computer science, including developing the necessary mathematical and computational skills, surveying the major design paradigms, and analyzing several specific algorithms and libraries. Therefore, a hands-on experience is clearly required and assignments are the best vehicle in this goal.

Every module will contain Assignments with problems sets that you will complete individually. Few questions will be completed by giving direct answers and most questions will be completed by a machine learning pipeline using a Jupyter notebook using your own code and certain open source libraries such as pandas, numpy, scikit-learn, etc. Generally, at the end of each assignment, there is one or two conclusion/evaluation question(s) about the problem at hand and about your pipeline's performance. A maximum of 100 points per problem set can be earned, with partial credit given as discussed below. Each problem set will be due by Day 7 of the module in which they are assigned. No late problems sets will be accepted without prior approval.

Submission

Submit each assignment as a Jupyter Notebook in original format (extension ipynb) file to the corresponding Assignment link within each module. Please use the following for naming your submission ‘Last Name–AssignX.ipynb’, where XX is the number of the module, i.e. [1-14].

Important: Before submitting your notebook assignments, please use Kernel → Restart & Run All. This will result running the notebook from reset. Then save and submit that copy. (Otherwise, some Code cells may not function when opened by your peers or the grader.)

Assignment Grading Considerations

Each Module Assignment will be worth a total of 100 points, divided among the problems in each set depending on their length and/or difficulty, and indicated at the beginning of the question. Problems will be graded for relevancy, accuracy, and completeness. The submitted Jupyter notebook is expected to run fully from the very beginning to the end after a clean kernel is started. Markdown cells can be used to explain the approach or Code comments must be included in the pipeline to present the audience or grader about the pipeline. The amount of explanations and comments must be reasonable like any other programming assignment. Solutions without justification will be not be considered complete and the grade will be adjusted down accordingly.

A note on academic dishonesty: While discussion of the homework is allowed, the assignments are intended to be done individually and you must prepare your solutions separately. If a code excerpt is used from other resources, then that code has to be paraphrased or made "your own" similar to writing a research paper. Direct copying of written work or computer code is considered to be dishonest and will result in a grade of zero on the assignment and possible an F in the course.

Instructor Role

The Assignment portion of the total course grade is the largest single contribution because it permits students to demonstrate their mastery of the concepts and their ability to program demonstrations. Therefore, I will be looking for consistent and dedicated attention to the problems every week. I will accept and answer questions (by Teams – preferred, by email, during Office Hours, or occasionally on the telephone) on the approach to any of the problems. In general, any responses to questions about the problems will be shared with the class so that everyone has the same information. Problem sets will be graded and returned weekly so that students may monitor their progress throughout the course. Detailed feedback will be provided on each assignment so that the student clearly understands any errors made and how to correct them.

Grading Policy

EP uses a +/- grading system (see “Grading System”, Graduate Programs catalog, p. 10).

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students.

This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University values diversity and inclusion. We are committed to providing welcoming, equitable, and accessible educational experiences for all students. Students with disabilities (including those with psychological conditions, medical conditions and temporary disabilities) can request accommodations for this course by providing an Accommodation Letter issued by Student Disability Services (SDS). Please request accommodations for this course as early as possible to provide time for effective communication and arrangements.

For further information or to start the process of requesting accommodations, please contact Student Disability Services at Engineering for Professionals, ep-disability-svcs@jhu.edu.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically. 

For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity. 
 
If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.