Independent Work Seminar Offerings - Fall 2024
Full details about the COS IW seminar offerings for the Fall 2024 semester can be found below.
Please note that the enrollment process for the fall independent work seminars differs from that of the spring. Students will directly-enroll in an open seminar through TigerHub.
Click here for information on how to enroll in a Fall 2024 independent work seminar.
COS IW 01: Natural Language Processing
Instructor: Christiane Fellbaum
Meeting Time: Fridays, 11:00 am - 12:20 pm
Location: CS Building, TBD
Abstract:
Natural Language Processing aims to understand and model properties of human language and the ways it is learned, produced and interpreted. Participants in the seminar will choose from a wide range of topics including but not limited to sentiment and opinion analysis, bias detection and mitigation, identification of fake news, computational humor, question answering and automated reasoning, financial market prediction, language puzzle generation, in English or another natural language. Additionally, past students have pursued projects in computational analyses of music, classifying composers or musical style. Each student will identify, scrape, clean and pre-process a dataset, using standard available resources. Data may come from available text corpora, news outlets, blogs, tweets, topic-specific forums (sports, food), etc. Students will apply (and possibly improve on) existing pre-processing tools for tokenization, lemmatizing, part-of-speech tagging, and syntactic parsing (the NLP "pipeline"). The focus will be on the analysis of explicit or implicit meaning in texts, on the word, sentence or document level. Students may wish to analyze linguistic data dealing with current political or social questions (e.g., gender/racial/nationality/religious bias). Different approaches to semantic analysis, using lexical resources and/or embeddings, will be considered and applied. Projects often (but not necessarily) include a machine learning component for students who have taken COS324. There's no course requirement beyond the 200-level COS classes. Students need not have prior independent research experience.
We will meet weekly as a group and discuss everyone's project, progress, challenges and findings. Students may work in pairs so long as each student covers a separate aspect of the project.
COS IW 02: Machine Learning and Data Science
Instructor: Xiaoyan Li
Meeting Time: Wednesdays, 11:00am - 12:20pm
Location: CS Building, TBD
Abstract:
In this seminar, you will review and apply various machine learning models for supervised and/or unsupervised machine learning tasks. Depending on your project, you may use models, such as Support Vector Machines, Decision Trees, Random Forest, Ridge regression, Lasso regression, Elastic Net regression, CNN, LSTM, and Kmeans clustering etc. Students will choose at least one data set of interest and propose some questions that can be answered from the data set by applying two or more machine learning models and performing data analysis. A complete process of data analysis consists of raw data collecting, feature extraction, missing data imputation, feature selection, model fitting, making predictions for unseen data, performance evaluation, and error analysis, etc. The goals of this seminar are helping students learn about the whole process of data analysis, understand a suite of machine learning methods, be able to compare and choose different types of methods for their data analysis tasks, and perform data analysis in real world applications without making some of the common mistakes. In addition, students are also encouraged to explore fairness and biases issues in the data sets they worked on and the machine learning algorithms they applied.
The prerequisites for this seminar are COS217, COS226, and COS324. Students should know Python already and understand the basic tasks of machine learning: classification, regression, and clustering, etc. You can use existing machine learning packages in Python and develop your own library if needed.
This seminar will meet once a week. Class times are used to present machine learning methods and data analysis techniques, and to discuss students’ project progress. Each student will report their weekly progress on their project and present in class on most of the weeks either in small groups or to the whole class. Students are expected to participate in class in both presenting their own projects and giving feedback to projects by their peers.
The first two classes will be used for discussing project ideas. Each student should develop an individual project which is suitable for one semester work and may have the potential to extend to a senior thesis. A thorough solid project may also lead to publication in some conference or workshop in the field.
The two sections of the seminar are independent but will generally be quite similar.
COS IW 03: Machine Learning and Data Science
Instructor: Xiaoyan Li
Meeting Time: Wednesdays, 3:00pm - 4:20pm
Location: CS Building, TBD
Abstract:
In this seminar, you will review and apply various machine learning models for supervised and/or unsupervised machine learning tasks. Depending on your project, you may use models, such as Support Vector Machines, Decision Trees, Random Forest, Ridge regression, Lasso regression, Elastic Net regression, CNN, LSTM, and Kmeans clustering etc. Students will choose at least one data set of interest and propose some questions that can be answered from the data set by applying two or more machine learning models and performing data analysis. A complete process of data analysis consists of raw data collecting, feature extraction, missing data imputation, feature selection, model fitting, making predictions for unseen data, performance evaluation, and error analysis, etc. The goals of this seminar are helping students learn about the whole process of data analysis, understand a suite of machine learning methods, be able to compare and choose different types of methods for their data analysis tasks, and perform data analysis in real world applications without making some of the common mistakes. In addition, students are also encouraged to explore fairness and biases issues in the data sets they worked on and the machine learning algorithms they applied.
The prerequisites for this seminar are COS217, COS226, and COS324. Students should know Python already and understand the basic tasks of machine learning: classification, regression, and clustering, etc. You can use existing machine learning packages in Python and develop your own library if needed.
This seminar will meet once a week. Class times are used to present machine learning methods and data analysis techniques, and to discuss students’ project progress. Each student will report their weekly progress on their project and present in class on most of the weeks either in small groups or to the whole class. Students are expected to participate in class in both presenting their own projects and giving feedback to projects by their peers.
The first two classes will be used for discussing project ideas. Each student should develop an individual project which is suitable for one semester work and may have the potential to extend to a senior thesis. A thorough solid project may also lead to publication in some conference or workshop in the field.
The two sections of the seminar are independent but will generally be quite similar.
COS IW 04: Computation and Machine Learning in Life Sciences and Biomedicine
Instructor: Yuri Pritykin
Meeting Time: Wednesdays, 11:00am - 12:20pm
Location: CS Building, TBD
Abstract:
In this seminar, students could work on a wide range of projects centered on the themes of preprocessing, analysis, integration, interpretation, visualization, manipulation and design of multi-dimensional data and experiments in life sciences and biomedicine. Examples of technologies and sources of data will include single-cell and spatial genomics, epigenomics, genome editing, imaging, biomedical literature, patient records, epidemiology, wearable devices. Ideas for potential projects will be suggested, and students are also free to choose their own topics. A special emphasis and ideas for projects this year will be around computational methods for design and analysis of multiplex CRISPR-based genome editing experiments.
The seminar will meet once a week. There will be two equivalent meetings per week, students should enroll for and attend only one of them. Class time will be used to introduce necessary concepts from biology and biotechnologies, interesting datasets and studies, computational methodology and software frameworks, but most of the time will be used to discuss students' progress in their projects. There are no prerequisites beyond COS217 and COS226. For most projects, knowing R or Python will be necessary, and students should be ready to pick it up in the first few weeks of the seminar. No prior knowledge of biology is required, but students should be ready to learn concepts from molecular biology and biotechnologies (necessary background and references will be provided, prior molecular biology or related background is a plus). Students may form teams to work on complementary aspects of a more ambitious project.
COS IW 05: Computation and Machine Learning in Life Sciences and Biomedicine
Instructor: Yuri Pritykin
Meeting Time: Thursdays, 11:00am - 12:20pm
Location: CS Building, TBD
Abstract:
In this seminar, students could work on a wide range of projects centered on the themes of preprocessing, analysis, integration, interpretation, visualization, manipulation and design of multi-dimensional data and experiments in life sciences and biomedicine. Examples of technologies and sources of data will include single-cell and spatial genomics, epigenomics, genome editing, imaging, biomedical literature, patient records, epidemiology, wearable devices. Ideas for potential projects will be suggested, and students are also free to choose their own topics. A special emphasis and ideas for projects this year will be around computational methods for design and analysis of multiplex CRISPR-based genome editing experiments.
The seminar will meet once a week. There will be two equivalent meetings per week, students should enroll for and attend only one of them. Class time will be used to introduce necessary concepts from biology and biotechnologies, interesting datasets and studies, computational methodology and software frameworks, but most of the time will be used to discuss students' progress in their projects. There are no prerequisites beyond COS217 and COS226. For most projects, knowing R or Python will be necessary, and students should be ready to pick it up in the first few weeks of the seminar. No prior knowledge of biology is required, but students should be ready to learn concepts from molecular biology and biotechnologies (necessary background and references will be provided, prior molecular biology or related background is a plus). Students may form teams to work on complementary aspects of a more ambitious project.
COS IW 06: Unsupervised Reinforcement Learning
Instructor: Benjamin Eysenbach
Meeting Time: Wednesdays, 11:00am - 12:20pm
Location: CS Building, TBD
Abstract:
In the same way that modern computer vision models can draw a picture of (nearly) anything and large language models can talk about (nearly) anything, we will study reinforcement learning (RL) algorithms for learning to do anything. While the standard RL problem looks at learning to solve a single task, this seminar will investigate algorithms that can learn skills for solving many tasks. Effective algorithms must therefore (1) propose their own goals, (2) learn effective representations of the environment, and (3) autonomously explore the environment.
Format: Working in pairs, students will conduct novel research on the design and analysis of unsupervised RL methods. We'll scope each project to make sure that each student has contributed a semester's-worth of work on the project. We'll spend the first few weeks reviewing prior methods and brainstorming projects. The rest of the semester will be devoted to working on the projects. The weekly meeting time will include a short update from a few groups and time to work on the projects. There will be a final paper due at the end of the semester
Prerequisites: The only hard prerequisite is COS324 (or similar) and a strong interest in reinforcement learning. COS435 (or similar) is recommended but not required. Students who haven't taken COS435 (or similar) before are highly encouraged to review relevant material over the summer.
Time expectations: I have high expectations for the students in this IW seminar. While an IW seminar may seem lightweight on paper (just one meeting per week), successful students will put the same time and rigor into this seminar as they put into other COS courses (e.g., COS 426, COS 433, COS 445).
If enrollment is full, please fill out this waitlist form, and register for section S99 in the meantime:
Waitlist form: https://forms.gle/RzT2zuXBTvDPF1iH6
COS IW 07: You Be the Prof
Instructor: David Walker
Meeting Time: Tuesdays, 11:00am - 12:20pm
Location: CS Building, TBD
Abstract:
Ever want to take over a course and show the prof how it's done? Now's your chance. In this IW seminar, develop technology, tools or materials to help other students learn. Doing so could
entail:
- Developing a creative assignment for an existing course (one you've taken already at Princeton) designed to teach students a concept in computer science;
- Developing a tool for teaching concepts in some other discipline outside of computer science.
- Creating an interactive, web-based tutorial on an interesting topic that you've wanted to learn about (like automata tutor: https://automata-tutor.model.in.tum.de/);
- Developing a tool, app or web-based platform to aid teaching computer science in some way; or
Examples of past projects in this seminar include:
- A tutorial on reinforcement learning using PyGame;
- A web-based interface and database for automating the creation of student study groups at Princeton;
- A personalized online flash card system for learning Korean with algorithms for spaced repetition to improve retention;
- An assignment for COS 326 involving Sudoku solving via SAT and theorem proving;
- A framework for hosting competitive COS 445 game theory assignments; and
- A practice tool to help Princeton students applying to naval flight school succeed on the ASTB-E (Aviation Selection Test Battery Exam)
If you've taken any class and can think of a way to improve it or know of some skill or idea or concept outside of computer science that you can use computer science to help teach, you can explore such a project in this seminar.
Enrollment Information, Fall 2024
Enrollment in the IW seminars for the fall is different than enrollment in the spring.
To enroll in a COS IW seminar for Fall 2024:
- BSE juniors: enroll in COS 397 in TigerHub and direct-enroll in the seminar section of your choice.
- BSE seniors: enroll in COS 497 in TigerHub and direct-enroll in the seminar section of your choice.
Seminar availability can be competitive so please enroll as soon as you are able if there is one that is of particular interest to you.
Please note: The COS 397 & COS 497 IW seminars share seats. If you are a senior, and the seminar section for COS 497 section is closed, but the COS 397 section is open, enroll in the course code with the open section, then email Mikki Hornstein, mhornstein (@princeton.edu) for help switching to the right course code and section. Same goes for juniors: if you are a junior and the seminar section for COS 397 is closed, but the COS 497 section is open, enroll in the course code with the open section, then email Mikki Hornstein, mhornstein (@princeton.edu) for help switching to the right course code and section. Seminar students do not need to complete anything in the IW portal at this time.
Questions? Please email Mikki Hornstein at mhornstein (@princeton.edu).
