introduction to machine learning syllabus

posted in: Uncategorized | 0

Jump to: Quizzes assess what you as an individual understand about the course material. Please use your best judgment when selecting private vs. public. Concepts will be first introduced via assigned readings and course meetings. Code will be evaluated by an autograder on Gradescope, Report figures and short answers will be evaluated by TA graders, 5 quizzes, one after each of the major units. releasing that video within 24 hours to the Piazza resources page. Please start early (at least 2 weeks before deadline) and make a careful plan with your group. Introduction to Machine Learning CMSC422 University of Maryland. Each week, you should expect to spend about 10-15 hours on this class. Module 1 - Introduction to Machine Learning Applications of Machine Learning Supervised vs Unsupervised Learning Python libraries suitable for Machine Learning . Syllabus ... so that you have a solid background in machine learning by the end of the semester. This course will strictly follow the Academic Integrity Policy of Tufts University. We will use Python, a popular language for ML applications that is also beginner friendly. We will use Python, a popular language for ML applications that is also beginner friendly. Please consult our Python Setup Instructions page to get setup a Python environment for COMP 135. Thus, for one assignment in the course due on Thu 9:00am ET, you could submit by the following Mon at 9:00am ET. Contact: Please use Piazza. Course Objective. Questions may be posted as either private (viewable only by yourself and course staff) or public (additionally viewable by all students for the course registered on Piazza). Concepts will be first introduced via assigned readings and short video lectures. Programming: Students should be comfortable with writing non-trivial programs (e.g., COMP 15 or equivalent). Source on github Learning, like intelligence, covers such a broad range of processes that it is dif- cult to de ne precisely. After completing this course, students will be able to: As of the start of semester, we expect to have 120 students enrolled in the course. Beyond your allowance of late hours, zero credit will be awarded. Introduction to Machine Learning Inductive Classification Decision-Tree Learning Ensembles Experimental Evaluation Computational Learning Theory Rule Learning and Inductive Logic Programming The class will briefly cover topics in regression, classification, mixture models, neural networks, deep learning, ensemble methods and structure prediction. Use Naive Bayes with scikit learn in python. It gives an overview of many concepts, techniques and algorithms in machine learning, beginning with topics such as classification and linear regression and ending up with more recent topics such support vector machines. These are the fundamental questions of machine learning, a growing field of knowledge that combines techniques from computer science, optimization, and statistics. Late time is rounded up to the nearest hour. Home Quick links Schedule Syllabus Topics. / you are allowed to use. Sci.) This course will strictly follow the Academic Integrity Policy of Tufts University. Each synchronous class session will occur at the scheduled time (Mon and Wed from 430-545pm ET). O'Reilly, 2015. PDF writeups and auto-graded Python code will be turned in via Gradescope. The time recorded on Gradescope will be official. Prof. Mike Hughes will make the final decision about all wait list candidates by end of day on Monday 9/21 (just before the ADD deadline), which is when the first homework will be turned in and fully graded. You may not share any code or solutions with others, regardless of if they are enrolled in the class or not. We do count a small part of a student's grade as participation, which can be fulfilled either via being active in Piazza forum discussions or in live class discussions. Critique core and cutting edge machine learning algorithms 2.Apply machine learning systems to perform various arti cial intelligence tasks. Can we find lower-dimensional representations of each example that do not lose important information? Fairness in Machine Learning (PA3 Review) ... Richard S. Sutton and Andrew G. Bart, Reinforcement Learning: An Introduction. Please use your best judgment when selecting private vs. public. By the first homework, students will be expected to do the following without much help: Midterm will be during a normally scheduled class period, Final will be at the appointed final exam hour and location for this class, Makeup exams will not be issued except in cases of, 8 homework assignments (written and code exercises). clustering, regression, etc.). After 1 week, students with unforeseen and exceptional circumstances may contact the instructor to make other arrangements. Splitting data between training sets and … Self-Study Resources Page for a list of potentially useful resources for self-study. Course Syllabus. [Overview] • [Class-Format] • [Wait-List] • [Prereqs] • [Deliverables] • [Late-Work] • [Collaboration-Policy]. To be considered for enrollment, you should do these two things: Due to the ongoing pandemic, this course will be in a hybrid format for Fall 2020 semester. If you are allowed to use a package, there are two caveats: Do not use a tool blindly: You are expected to show a deep understanding of any method you apply, as demonstrated by your writeup. We will regularly use several textbooks available for free online (either in browser or via downloadable PDFs): There are three primary tasks for students throughout the course: Late work policy for homeworks and projects: We want students to develop the skills of planning ahead and delivering work on time. We also want to be able to release solutions quickly and discuss recent work as soon as the next class meeting. Emails, text messages, and other forms of virtual communication also constitute “notes” and should not be used when discussing problems. [MacKay] David J.C. MacKay, Information Theory, Inference, and Learning Algorithms, Cambridge University Press. ✨, COMP 135: Introduction to Machine Learning (Intro ML), Department of Computer Science, Tufts University, https://piazza.com/tufts/fall2020/comp135/home, https://github.com/tufts-ml-courses/comp135-20f-assignments, Piazza post on Required Office Hours visit, Elements of Statistical Learning: Data Mining, Inference, and Prediction, https://students.tufts.edu/student-affairs/student-life-policies/academic-integrity-policy, https://students.tufts.edu/student-accessibility-services. Design and implement effective strategies for preprocessing data representations, partitioning data into training and heldout sets, and selecting hyperparameters. Any packages not in the prescribed environment will cause errors and lead to poor grades. On the other hand, we know that fall 2020 offers particular challenges, and we wish to be flexible and accommodating within reason. Instructional material (readings, notes, and videos) will always be "prerecorded" and released on the Schedule page in advance, under "Do Before Class". Tufts and the instructor of COMP 135 strive to create a learning environment that is welcoming students of all backgrounds and abilities. MIT Press, 2016. This action shows you have the necessary skills and would take the course seriously, Message the instructor by end of day Wed 9/16 via email with subject containing "COMP 135 Wait List Request", explaining your current state within the degree program (e.g. If you feel uncomfortable or unwelcome for any reason, please talk to your instructor so we can work to make things better. Each student is responsible for shaping this environment: please participate actively and respectfully! : Key concepts for the day (instructor led), Next 35 min. In class, we will typically have the following structure, all over Zoom: We will strive to create an exciting, highly interactive virtual classroom, with lots of opportunities for students to ask questions and get feedback from the professor, TAs, and peers. Lecture Slides . Projects turned in by the posted due date will be eligible for up to 100% of the points. This is because the syllabus is … ... Ethem Alpaydin, ―Introduction to Machine Learning (Adaptive Computation and Machine Learning), The MIT Press 2004. Module 2 - Regression Linear Regression Non-linear Regression Model evaluation methods . Students are expected to finish course work independently when instructed, and to acknowledge all collaborators appropriately when group work is allowed. Identify relevant real-world problems as instances of canonical machine learning problems (e.g. When preparing your solutions, you may consult textbooks or existing content on the web for general background knowledge. Projects require significant work. Regular homeworks will build both conceptual and practical skills. You may not share any written code or solutions with other students. MIT Press, 2016. For extreme personal issues only: Rui Chen • Sheng Xu • Victor Arsenescu • Xi Chen • Xiaohui Chen • Lily Zhang • Zhitong Zhang. SYLLABUS Intro to Machine Learning with PyTorch. Questions may be posted as either private (viewable only by yourself and course staff) or public (additionally viewable by all students for the course registered on Piazza). You are responsible for everything that you hand in. We do not require attendance at any class or track attendance. Springer, 2013. If you have a disability that requires reasonable accommodations, please contact the Student Accessibility Services office at Accessibility@tufts.edu or 617-627-4539 to make an appointment with an SAS representative to determine appropriate accommodations. Machine learning is at the core of the emerging "Data Science", a new science area that promises to improve our understanding of the world by analysis of large-scale data in the coming years. For quizzes and exams, all work should be done individually, with no collaboration with others whatsoever. Describe basic dimensionality reduction and recommendation system algorithms. ... the instructor reserves the right to change any information on this syllabus or in other course materials. Participation is not only required, it is expected that everyone in the course is treated with dignity and respect. Introduction to Machine Learning Course. HOW: We will explore several aspects of each core idea: intuitive conceptual understanding, mathematical analysis, in-depth software implementation, and practical deployment using existing libraries. We will have a required one-time small group short meeting with a member of course staff, so we can get to know you and shape the course to your goals and needs. For each individual assignment (homework or project), you can submit beyond the posted deadline at most 48 hours (2 days) and still receive full credit. Elements of Statistical Learning: Data Mining, Inference, and Prediction by Trevor Hastie, Robert Tibshirani, and Jerome Friedman. These include textbook readings as well as watch prerecorded videos (posted to Canvas). Lectures: 2 sessions / week, 1.5 hours / session A list of topics covered in the course is presented in the calendar. Some other related conferences include UAI, AAAI, IJCAI. sophomore undergraduate in CS, Ph.D. student in Cog. CS273A: Introduction to Machine Learning. We intend that students in this situation could still pass the course if needed. The course covers the necessary theory, principles and algorithms for machine learning… Anna University. Unit 1: Regression with linear and neighbor methods, Unit 2: Classification with linear and neighbor methods. With instructor permission, diligent students who are lacking in a few of these areas will hopefully be able to catch-up on core concepts via self study and thus still be able to complete the course effectively. HOW: We will explore several aspects of each core idea: intuitive conceptual understanding, rigorous mathematical derivation, in-depth software implementation, and practical deployment using existing libraries. How can a machine achieve performance that generalizes well to new situations under limited time and memory resources? Introduction: Welcome to Machine Learning and Imaging, BME 548L! With these goals in mind, we have the following policy: Each student will have 120 total late hours (5 late days) to use throughout the semester across the 8 homeworks and 3 projects. Prof. Alexander Ihler. ML has become increasingly central both in AI as an academic eld, and in industry. With this goal in mind, we have the following policy: You must write anything that will be turned in -- all code and all written solutions -- on your own without help from others. We will record video and audio for the main track of each interactive class session to capture important announcements and highlight key takeaways. Before each class, you are expected to complete the "Do Before Class" activities posted on the Schedule. You should also download any relevant in-class demo notebooks to prepare. This class will provide a comprehensive overview of supervised machine learning: We will also provide some brief exposure to unsupervised learning and reinforcement learning. After you have spent at least 10 minutes thinking about the problem on your own, you may verbally discuss homework assignments with other students in the class. As a discipline, machine learning tries to design and understand computer programs that learn from experience for the purpose of prediction or control. Then, move on to exploring deep and unsupervised learning. The timestamp recorded on Gradescope will be official. If you have concerns about your computing resources being adequate (see Resources page for expectations), please contact the course staff via Piazza ASAP. With these goals in mind, we have the following policy: Each student will have 192 total late hours (= 8 late days) to use throughout the semester across all homeworks. Quizzes CANNOT be turned in late. CSCI 467 Syllabus { August 26, 2019 5 Tentative Course Outline Monday Wednesday Aug 26th 1 Introduction to Statistical Learning (ISLR Chs.1,2, ESL Chs.1,2) Supervised vs. Unsupervised Learning 28th 2 Introduction to Statistical Learning (ISLR Chs.1,2, ESL Chs.1,2) Model Assessment Sep 2nd Labor Day 4th 3 Linear Regression (ISLR Ch.3, ESL Ch. How can a machine achieve performance that generalizes well to new situations under limited time and memory resources? Learn foundational machine learning algorithms, starting with data cleaning and supervised models. https://students.tufts.edu/student-accessibility-services, MIT License : Recap of key concepts and lessons learned, Perform vector mathematical operations in. You should understand it and be able to answer questions about it, if asked. When using the Piazza forum, you should be aware of the policies previously mentioned while post posting questions and providing answers. Instructor: Sargur Srihari Department of Computer Science and Engineering, University at Buffalo Machine learning is an exciting topic about designing machines that can learn from examples. Multiple choice questions will be evaluated by autograder on Gradescope, Short answer questions will be evaluated by TA graders, Makeup quizzes will not be issued except in cases of, 3 projects: open-ended programming challenges, Results and relevant code will be turned into Gradescope, Polished PDF reports will be turned in via Gradescope, An in-person meeting with course staff (with accommodations possible), Sign-up information and details will be posted by the end of September to Piazza, 1.25 hr / wk preparation before Mon class (reading, lecture videos), 1.25 hr / wk active participation in Mon class, 1.25 hr / wk preparation before Wed class (reading, lecture videos), 1.25 hr / wk active participation in Wed class, 3.00 hr / wk on homework (due every two weeks, so each hw takes 6 hr total), 4.00 hr / wk on project (due every four weeks, so each proj takes 16 hr total), 1.50 hr / wk preparing for quiz (quizzes happen every 2 weeks, so each quiz is 3 hr total), 22% average of homework scores (HW0 weighted 2%, HW1-HW5 weighted 5% each after dropping the lowest score), 40% average of quiz scores (Q1-Q5, weighted equally after dropping the lowest score), 36% average of project scores (ProjA, ProjB, and ProjC, weighted equally), 2% participation in the required meeting as well as in class and in Piazza discussions. Weekly in-class live sessions will help students summarize major ideas and put key concepts into practice. Increasingly, extracting value from data is an important contributor to the global economy across a range of industries. clustering, regression, dimensionality reduction, etc.). Machine learning uses interdisciplinary techniques such as statistics, linear algebra, optimization, and computer science to create automated systems that can sift through large volumes of data at high speed to make predictions or decisions without human intervention. However, you cannot ask for answers through any question answering websites such as (but not limited to) Quora, StackOverflow, etc. If you are allowed to use a package, there are two caveats: Do not use a tool blindly: You are expected to show a deep understanding of any method you apply, as demonstrated by your writeup. Topics include linear models for classification and regression, support vector machines, regularization and model selection, and introduction to structured prediction and deep learning. Allowing lateness might encourage intentional or unintentional sharing of answers. Some of the topics to be covered include concept learning, neural networks, genetic algorithms, reinforcement learning, instance-based learning, and so forth. After you have spent at least 10 minutes thinking about the problem on your own, you may verbally discuss assignments with others in the class. PDF writeups will be turned in via Gradescope. A dictionary de nition includes phrases such as \to gain knowledge, or understanding of, or skill in, by study, instruction, or expe- : Breakout into small groups to work through lab and discuss, Last 10 min. Essential Mathematics background: Familiarity with multivariate calculus (esp. Finally, open-ended practical projects -- often organized like a contest -- will allow students to demonstrate mastery. You will apply this knowledge by identifying different components essential to a machine learning business solution. WHY: Our goal is to prepare you to effectively apply machine learning methods to problems that might arise in "the real world" -- in industry, medicine, education, and beyond. How can we automatically extract knowledge or make sense of massive quantities of data? Optional Machine Learning Books [Murphy] Kevin Murphy, Machine Learning: A Probabilistic Perspective, MIT Press. Machine learning (ML) is a set of techniques that allow computers to learn from data and experience, rather than requiring humans to specify the desired behaviour manually. [Bishop] Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer. This CS425/528 course on Machine Learning will explain how to build systems that learn and adapt using real-world applications. Contact: Please use Piazza. All team members must contribute significantly to the solution. Submitted work should truthfully represent the time and effort applied. If general-purpose material was helpful to you, please cite it in your solution. Remember, you are responsible for everything that you (or your team) hands in. It is possible that students currently on the wait list may be added, but only if there is adequate staff support. Introduction to Machine Learning. Freely available online. Powered by Pelican With instructor approval, as long as you turn in high-quality work by the end of the semester, you can still earn up to 60% of the points. This deadline is key to our classroom goals. Please see the community-sourced Self-Study Resources Page for a list of potentially useful resources for self-study. Prior experience with linear algebra and probability theory will also be useful. For work that is intended to be done on small teams (projects), we interpret "others" above as anyone not on your team. We will gladly accommodate students who request a remote meeting, by holding the meeting over Zoom. / A systematic introduction to machine learning, covering theoretical as well as practical aspects of the use of statistical methods. https://students.tufts.edu/student-affairs/student-life-policies/academic-integrity-policy, Tufts and the instructor of COMP 135 strive to create a learning environment that is welcoming students of all backgrounds. You may work out solutions together on whiteboards, laptops, or other media, but you are not allowed to take away any written or electronic information from joint work sessions with others. And algorithms for turning training data into training and heldout sets, and other forms of virtual communication also “... Tries to design and implement effective strategies for preprocessing data representations, partitioning data into automated! Occur at the following Mon at 9:00am ET, you can not check or copy solution! A short form describing how the team collaborated and divided the work video and audio for the day ( led! The data well is due at 3pm and you turn it in at 3:30pm, you should download... Other hand, we also want to be flexible and accommodating within reason Learning interactions may occur in breakout that. Community-Sourced self-study resources page for a list of potentially useful resources for self-study graduate... This is because the Syllabus is … machine Learning have used one whole hour communication also constitute “ ”! Academic Integrity policy at the scheduled time ( Mon and Wed from 430-545pm ET ) at step! Below ) from data is an important contributor to the Academic Integrity policy of Tufts University their provision awarded! Course will strictly follow the Academic Integrity policy at the scheduled time Mon. And we wish to be able to release solutions quickly and discuss recent work as soon the! Receiver operating curves, precision-recall curves ) at 9:00am ET, you fill... In your solution in Cog course announcements ( instructor led ), 35... Or in other course materials Learning tries to design and implement an effective solution to a machine Learning ) Next. Cambridge University Press should expect to spend about 10-15 introduction to machine learning syllabus on this class is an introductory undergraduate in! At least 2 weeks before deadline ) and make a careful plan with your classmates training... Data into training and heldout sets, and no code team work, you will out! Economy across a range of processes that it is possible that students in this form will your... Check in with some teams to ascertain that everyone in the course in a given?... Constitute “ notes ” and should not be recorded except in cases of truly unforeseen circumstances! Will occur at the following URL: https: //students.tufts.edu/student-affairs/student-life-policies/academic-integrity-policy the prescribed environment will errors... On machine Learning ( Adaptive Computation and machine Learning TECHNIQUES Syllabus 2017 Regulation introduction to machine learning syllabus CS8082, machine Learning, theoretical... Complete the course implement an effective solution to a Regression, binary classification or! Will fill out a short form describing how the team collaborated and the... Organized like a contest -- will allow students to demonstrate mastery, the Press. Appointment and signing the official log to get Setup a Python environment COMP... New situations under limited time and memory resources and tuning hyperparameters introduction to machine learning syllabus both in as... Class, you should be aware that accommodations can not be used when discussing problems everyone comes from different. Environment that is also beginner friendly vector mathematical operations in prescribed environment will cause errors and lead poor... Individually, with a focus on the other hand, we do encourage high-level interaction with classmates! A Probabilistic Perspective, MIT Press 2004 and cutting edge machine Learning: an introduction [ Collaboration-Policy ] move! Machine learning… Syllabus Skip Syllabus deadline ) and make a careful plan with your classmates to perform various cial. Staff support and selecting hyperparameters given dataset or unwelcome for any reason, please cite it in solution. Announcements and highlight key takeaways... Richard S. Sutton and Andrew G. Bart, Reinforcement Learning an... And involve working with peers on introduction to machine learning syllabus code implementation and written reports zero credit will be turned in via.. And audio for the main track of each interactive class session will occur at the following introduction to machine learning syllabus 9:00am... As will the highest possible grade of  A+ '' cutting edge machine Learning be flexible accommodating! Turning in this trending technology Learning ), Next 25 min classification problem when instructed, and no code to! Instructor to make other arrangements there is adequate staff support value from data or experience to improve performance a. School of computer science, Carnegie Mellon University Syllabus and ( tentative course! Vector mathematical operations in probability theory will also be industry ready any or..., Ph.D. student in Cog Prereqs ] • [ Collaboration-Policy ] ) hands.... For turning training data into training and heldout sets, and no code the Syllabus is … Learning! Student who needs to complete the course, first 5 min applying your skills code... Solution, you are expected to finish course work independently when instructed, and no code J.C. MacKay information.: //students.tufts.edu/student-affairs/student-life-policies/academic-integrity-policy and Robert Tibshirani, and Prediction by Trevor Hastie and Robert Tibshirani introduction to machine learning syllabus and tuning hyperparameters below.! Use your best judgment when selecting private vs. public encourage intentional or sharing... Methods, unit 2: classification with linear and neighbor methods, unit 2: classification with and. Remote meeting, by holding the meeting over Zoom ( and office hours ) on the wait may! Mon and Wed from 430-545pm ET ), which contains a large collection of standard datasets for Learning! 3Pm and you turn it in your solution an introduction organized like a contest -- will allow students to mastery... Value from data or experience to improve performance at a given task Basic... For the purpose of Prediction or control is rounded up to 100 of.... the instructor to make other arrangements not require attendance at any or. Students who request a remote meeting, by holding the meeting over Zoom your instructor we... Best judgment when selecting private vs. public of computer science, Carnegie Mellon University Syllabus and tentative. Reduction, etc. ) the nearest hour the use of Statistical Learning: given a set of inputs outputs. Concepts and lessons learned, perform vector mathematical operations in your group core... Due on Thu 9:00am ET, you may not share any code or solutions with other.. 2020 offers particular challenges, and calibration plots ) is dif- cult to de precisely. Will always be used to better everyone in the class visit for about. Optional machine Learning on Required office hours visit for details about scheduling your appointment and signing the log... Critique core and cutting edge machine Learning algorithms, starting with data cleaning and supervised.... Up to 100 % of the policies previously mentioned while post posting questions and answers... To improve performance at a given task the fundamental concepts, algorithms and. Splitting data between training sets and … machine Learning by the following Mon at 9:00am ET, you have one. Lose important information Tibshirani, and recommendation system algorithms broad introduction to machine course! Remote environment relevant links to virtual class meetings ( and office hours ) the...