Email: farzadk[at]illinois.edu
Office Hour: Open
Website:
Email: ukamaci2[at]illinois.edu
Office Hour: TBD
Work submission logistics.
Gradescope for assignments (self-enrollment code EV6W7W ): [link]
In this course, you will learn how to use auto-differentiation tools like PyTorch, how to leverage them for basic machine learning algorithms (linear regression, logistic regression, deep nets, k-means clustering), and how to extend them with custom methods to fit your needs. Auto-differentiation is one of the most important tools for data analysis and a solid understanding is increasingly important in many disciplines. In contrast to existing courses that focus on algorithmic and theoretical aspects, here we focus on studying material that permits deploying auto-diff tools to your area of interest. Pre-requisites: Math 257 (Linear Algebra with Computational Applications) or equivalent, basic probability, and proficiency in Python. Recommended Reference Texts: (1) Pattern Recognition and Machine Learning by Christopher Bishop (2) Machine Learning: A Probabilistic Perspective by Kevin Murphy (3) Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
Please note that these books are more comprehensive than the material covered in this class. Course Deliverables: (1) Homeworks (submission on Gradescope) (2) Midterm Exams: There will be two midterm exams.
40% Homeworks; 30% each Midterm
The syllabus is subject to minor changes.
Event | Date | Description | Materials | Assignments |
---|---|---|---|---|
Lecture 1 | 08/27/2024 | Intro and software install | , | |
Lecture 2 | 08/29/2024 | Pytorch tensors, views, indexing | ||
Lecture 3 | 09/03/2024 | Pytorch storage, advanced indexing, CPU/GPU, data types | ||
Lecture 4 | 09/05/2024 | Pytorch functions | ||
Lecture 5 | 09/10/2024 | Linear algebra and differentiation w.r.t. vectors/matrices | ||
Lecture 6 | 09/12/2024 | Pytorch matrix | ||
Lecture 7 | 09/17/2024 | Automatic differentiation 1 | ||
Lecture 8 | 09/19/2024 | Automatic differentiation 2 | ||
Lecture 9 | 09/24/2024 | Automatic differentiation 3 | ||
Lecture 10 | 09/26/2024 | Primal optimization | ||
Lecture 11 | 10/01/2024 | Linear regression 1 | ||
Lecture 12 | 10/03/2024 | Linear regression 2 | ||
Lecture 13 | 10/08/2024 | Review for MT1 | ||
Lecture 14 | 10/10/2024 | Midterm 1 (in class) | ||
Lecture 15 | 10/15/2024 | Pytorch optimizers | ||
Lecture 16 | 10/17/2024 | Pytorch dataset | ||
Lecture 17 | 10/22/2024 | Pytorch dataloaders | ||
Lecture 18 | 10/24/2024 | Logistic regression | ||
Lecture 19 | 10/29/2024 | Multiclass logistic regression | ||
Lecture 20 | 10/31/2024 | Deep nets 1 | ||
Lecture 21 | 11/05/2024 | |||
Lecture 22 | 11/07/2024 | Deep nets 2 | ||
Lecture 23 | 11/12/2024 | Deep nets 3 | ||
Lecture 24 | 11/14/2024 | Special topics (TBD) | ||
Lecture 25 | 11/19/2024 | Special topics (TBD) | ||
Lecture 26 | 11/21/2024 | Special topics (TBD) | ||
Break | 11/26/2024 | Thanksgiving | ||
Break | 11/28/2024 | Thanksgiving | ||
Lecture 27 | 12/03/2024 | Special topics (TBD) | ||
Lecture 28 | 12/05/2024 | Special topics (TBD) | ||
Lecture 29 | 12/10/2024 | Midterm 2 (in class) |
Time: Mon/Wed 10:15am-11:44am
Location: Town 100
Instructors: Prof. Dinesh Jayaraman ([email protected]) Prof. Mingmin Zhao ([email protected])
Office Hours: We are currently holding the office hours listed below.
Name | Time slot | Location |
---|---|---|
Prof. Dinesh Jayaraman | TBD | TBD |
Prof. Mingmin Zhao | TBD | TBD |
Tongtong Liu | TBD | TBD |
Zelong Wang | TBD | TBD |
Chandler Cheung | TBD | TBD |
Deeksha Sethi | TBD | TBD |
Edward Hu | TBD | TBD |
Guangyao Dou | TBD | TBD |
Haorui Li | TBD | TBD |
Harshwardhan Yadav | TBD | TBD |
Helen Nguyen | TBD | TBD |
Jianing Qian | TBD | TBD |
Jocelyn Gao | TBD | TBD |
Wendy Deng | TBD | TBD |
Collaboration policy: You are responsible for knowing Penn's Code of Academic Integrity . In particular, copying solutions from other students or other resources (e.g. the web or from students who have taken the class in previous years) is NOT allowed. Making answers to homeworks or exams available to others either directly or by posting on the web is also NOT allowed. We will not have a sense of humor about violations of this policy!
AI/LLM policy: Modern AI tools (e.g., ChatGPT, Claude, Gemini, etc.) can be of great help in understanding concepts, and we have no concerns about you using them to get alternative explanations for topics. Always dig a bit deeper when learning from an LLM, like following up links to make sure the LLM did not simply make something up. Given that we are trying to teach general, reusable skills -- we expect you to write your homework without help from an LLM or from a classmate. Please note that the exams will be tailored with this in mind (i.e., closed-book exams focusing on the ability to tackle problems) so you should make sure you can solve problems on your own!
Links: We will use Ed Discussion for questions and communication, and GradeScope to submit assignments. Canvas is just the “official” LMS of the university, but in practice we will not use it very much after the first week. It serves as the hub for Gradescope, Ed Forum etc. All other materials will be posted on the course website. We encourage students to use Google Colab for coding assignments.
Waitlist: We have a very large amount of demand for just a few remaining slots in the class. As such, we are currently only considering students who are graduating this fall and who need to take the course this fall for credit to graduate. In addition, all prerequisites must be satisfied and all waitlist application questions must have been answered correctly, and all decisions are at the discretion of the instructors. Please only reach out to us if you believe you qualify and have not yet heard back.
Attendance: We expect students to attend classes regularly; weekly quizzes designed to make sure students are following course material. However, please do not come to class if you are not feeling well or test positive for Covid-19. We will provide course recordings (on Canvas) and lecture notes (on this website) for students unable to make it to class.
Description: Machine learning has been essential to the success of many recent technologies, including autonomous vehicles, search engines, genomics, automated medical diagnosis, image recognition, and social network analysis. This course will introduce the fundamental concepts and algorithms that enable computers to learn from experience, with an emphasis on their practical application. It will introduce supervised learning (linear and logistic regression, decision trees, neural networks and deep learning, and Bayesian networks), unsupervised learning (clustering and dimensionality reduction), and reinforcement learning.
CIS 4190 vs. 5190: This course has an undergraduate version (CIS 4190) and a graduate version (CIS 5190). The lectures are the same, but you may be evaluated differently on your homeworks and projects; in particular, some homeworks will have components that are mandatory for CIS 5190 but optional for CIS 4190. Importantly, since the two versions have different requirements, you cannot complete the course as CIS 4190 and petition afterwards to have it changed to CIS 5190 for graduate credit.
CIS 5190 vs. 5200: Penn CIS offers two different introductory machine learning courses: CIS 4190/5190 (Applied Machine Learning) and CIS 5200 (Machine Learning). While there is overlap, the former (this course!) emphasizes practical application of existing machine learning methods, whereas the latter emphasizes the statistical foundations and theory of ML. CIS 5190 is NOT a prerequisite for CIS 5200. It makes little sense to take both courses (though taking CIS 4190/5190 and later CIS 5200 is possible).
CIS 5190 vs. 5450: Penn CIS also offers CIS 5450, which offers a holistic view of the data science pipeline, including data wrangling, data visualization, machine learning, and scalable data processing. In contrast, this course focuses primarily on machine learning, covering machine learning algorithms in greater breadth and depth. The two courses can be taken in either order, but students should consider taking CIS 5450 first.
Prerequisites: Introductory probability and statistics, multivariable calculus, and linear algebra are required (HW 0 will test your knowledge of this material). In addition, you are expected to be able to program comfortably in some language. We will use Python throughout the course, and can help you pick it up (primer + office hours). If you are not confident of your coding skills in any language at all, the homework may be very difficult.
Textbook: There is no required textbook, but you can find useful resources here .
This grading scheme is tentative and will be finalized soon.
Homework (25%): There will be 5 homework assignments, each containing both a written component and a coding component. The written portion will be submitted via GradeScope; the coding portion will be submitted both via GradeScope and programmatically to an autograder. Detailed instructions will be provided in the assignment.
Project (30%): We will provide more details on the final project shortly.
Mid-term Exams (30%): There will be two Mid-term exams, one in the middle of the semester and one at the end. The exams will be closed-book and will test your understanding of the material covered in the course.
Quizzes (10%): There will be 12 (roughly weekly) quizzes testing basic understanding of the material covered that week; these will be submitted on GradeScope. You will receive full credit if you correctly answer at least 50% of the questions.
Good citizenship points (5%): Everyone has them by default, you can lose them for disruptive behaviors in class/on Ed discussions.
Grading scheme: A+: 90+, A: 85-90, A-: 80-85, B+: 75-80, B: 70-75, B-: 65-70, lower passing grades: 50-65. Grades might be curved, but only upwards. i.e. your grade will only improve.
Late policy: For homework assignments, you will lose 0.5% per late hour (rounded up), with a maximum of 48 late hours per assignment. For example, if you submit HW 1 20 hours late, you lose 10% of points on HW 1 (which is 0.5% of your overall course grade). If you have medical reason for an extension, send both professors a copy of your medical visit report, and we will grant an penalty-free extension (typically 2 days); we will consider other requests on a case-by-case basis.
Js versions, js functions, js html dom, js browser bom, js web apis, js vs jquery, js graphics, js examples, js references, javascript assignment, javascript assignment operators.
Assignment operators assign values to JavaScript variables.
Operator | Example | Same As |
---|---|---|
= | x = y | x = y |
+= | x += y | x = x + y |
-= | x -= y | x = x - y |
*= | x *= y | x = x * y |
/= | x /= y | x = x / y |
%= | x %= y | x = x % y |
**= | x **= y | x = x ** y |
Operator | Example | Same As |
---|---|---|
<<= | x <<= y | x = x << y |
>>= | x >>= y | x = x >> y |
>>>= | x >>>= y | x = x >>> y |
Operator | Example | Same As |
---|---|---|
&= | x &= y | x = x & y |
^= | x ^= y | x = x ^ y |
|= | x |= y | x = x | y |
Operator | Example | Same As |
---|---|---|
&&= | x &&= y | x = x && (x = y) |
||= | x ||= y | x = x || (x = y) |
??= | x ??= y | x = x ?? (x = y) |
The Simple Assignment Operator assigns a value to a variable.
The += operator.
The Addition Assignment Operator adds a value to a variable.
The -= operator.
The Subtraction Assignment Operator subtracts a value from a variable.
The *= operator.
The Multiplication Assignment Operator multiplies a variable.
The **= operator.
The Exponentiation Assignment Operator raises a variable to the power of the operand.
The /= operator.
The Division Assignment Operator divides a variable.
The %= operator.
The Remainder Assignment Operator assigns a remainder to a variable.
Advertisement
The Left Shift Assignment Operator left shifts a variable.
The >>= operator.
The Right Shift Assignment Operator right shifts a variable (signed).
The >>>= operator.
The Unsigned Right Shift Assignment Operator right shifts a variable (unsigned).
The &= operator.
The Bitwise AND Assignment Operator does a bitwise AND operation on two operands and assigns the result to the the variable.
The |= operator.
The Bitwise OR Assignment Operator does a bitwise OR operation on two operands and assigns the result to the variable.
The ^= operator.
The Bitwise XOR Assignment Operator does a bitwise XOR operation on two operands and assigns the result to the variable.
The &&= operator.
The Logical AND assignment operator is used between two values.
If the first value is true, the second value is assigned.
The &&= operator is an ES2020 feature .
The Logical OR assignment operator is used between two values.
If the first value is false, the second value is assigned.
The ||= operator is an ES2020 feature .
The Nullish coalescing assignment operator is used between two values.
If the first value is undefined or null, the second value is assigned.
The ??= operator is an ES2020 feature .
Use the correct assignment operator that will result in x being 15 (same as x = x + y ).
Start the Exercise
If you want to use W3Schools services as an educational institution, team or enterprise, send us an e-mail: [email protected]
If you want to report an error, or if you want to make a suggestion, send us an e-mail: [email protected]
Top references, top examples, get certified.
We use some essential cookies to make this website work.
We’d like to set additional cookies to understand how you use GOV.UK, remember your settings and improve government services.
We also use cookies set by other sites to help us deliver content from their services.
You have accepted additional cookies. You can change your cookie settings at any time.
You have rejected additional cookies. You can change your cookie settings at any time.
The UK government announced a new project today that will enhance AI's ability to assist teachers in marking work and planning lessons.
Using AI tools to help reduce teachers' workload.
Artificial intelligence will be better at helping teachers mark work and plan lessons under a new project announced by the UK government today.
The project, backed by £4 million of government investment, will pool government documents including curriculum guidance, lesson plans and anonymised pupil assessments which will then be used by AI companies to train their tools so they generate accurate, high-quality content, like tailored, creative lesson plans and workbooks, that can be reliably used in schools.
The content store is targeted at technology companies specialising in education to build tools which will help teachers mark work, create teaching materials for use in the classroom and assist with routine school admin.
It comes as new research shows parents want teachers to use generative AI to enable them to have more time helping children in the classroom with face-to-face teaching – supporting the government’s mission to break down barriers to opportunity. However, teachers and AI developers are clear better data is needed to make these technologies work properly, which this project looks to help with.
Science Secretary Peter Kyle said:
We know teachers work tirelessly to go above and beyond for their students. By making AI work for them, this project aims to ease admin burdens and help them deliver creative and inspiring lessons every day, while reducing time pressures they face. This is the first of many projects that will transform how we see and use public sector data. We will put the information we hold to work, using it in a safe and responsible way to reduce waiting lists, cut backlogs and improve outcomes for citizens across the country.
Minister for Early Education Stephen Morgan said:
We are determined to break down the barriers to opportunity to ensure every child can get the best possible education – and that includes access to the best tech innovations for all. Artificial Intelligence, when made safe and reliable, represents an exciting opportunity to give our schools leaders and teachers a helping hand with classroom life. Today’s world-leading announcement marks a huge step forward for AI in the classroom. This investment will allow us to safely harness the power of tech to make it work for our hard-working teachers, easing the pressures and workload burdens we know are facing the profession and freeing up time, allowing them to focus on face-to-face teaching.
The content store, backed by £3 million, is a first-of-its kind approach to processing government data for AI , as the UK government forges ahead with using technology to transform public services and improve lives people across the country.
It includes a partnership with the Open University which is sharing learning resources to be drawn on as part of the project.
This follows Department for Education tests, published today, which show providing generative AI models with this kind of data can increase accuracy to 92%, up from 67% when no targeted data was provided to a large language model.
Minister Morgan announced the project today during a speech to international education ministers at the Global Education Innovation Summit ( GEIS ) in Seoul, Republic of Korea. The three-day event, on the theme of “classroom revolution led by teachers with AI ” will see the launch of the Global Education and Innovation Alliance, of which the UK will be of the founding members.
He told the delegation the world-leading initiative will mark the first government-approved store of high-quality education material optimised for AI product development and will stimulate the production of safe, legally compliant, evidence-based tools, relevant to our teachers’ needs.
To encourage AI companies to make use of the datastore, a share of an additional £1 million will be awarded to those who bring forward the best ideas to put the data into practice to reduce teacher workload. Each winner will build an AI tool to help teachers specifically with feedback and marking by March 2025, with applications opening on 9th September.
Almost half of teachers are already using AI to help with their work, according to a survey from TeacherTapp, but current AI tools are not specifically trained on the documents setting out how teaching should work in England.
Chris Goodall, a teacher and Head of Digital Education in the Bourne Education Trust, first started using AI when he was teaching business in November 2022. Here, Chris experimented with using ChatGPT to develop a range of lesson activities, such as personalised case studies, to complement his lessons.
Now, Chris supports teachers across over 26 primary, secondary and specialist schools in the Trust to enhance their lessons and cut down the time they need to spend on admin by using AI .
With his support, teachers have used generative AI to evaluate their curriculum materials, create case studies and other activities to create engaging lessons. Teachers at Auriol Junior School even illustrated a teacher-written guide encouraging students to read more books with AI -generated text, cartoon creatures and music, encouraging students to become a “literacy monster” and making the programme more engaging.
Chris Goodall, a teacher and Head of Digital Education in the Bourne Education Trust, said:
AI has been a hugely powerful tool for me and my colleagues at the Bourne Education Trust. It allows us to create engaging, personalised learning experiences for our students while also significantly reducing the time taken to create them. Personally, I’ve used AI to quickly generate scaffolded activities, adapt materials for students with special educational needs, and create more engaging lessons that are accessible to all. The time saved allows school staff to focus on what matters most, interacting with students and providing individualised feedback and support. The content store will take this to the next level by offering easy access to high quality evidence based and legally compliant education materials. Developed with input from educators it supports effective teaching practices and fosters collaboration and innovation. This initiative demonstrates how AI , when implemented responsibly and ethically, can support and empower teachers to create more dynamic, personalised learning experiences for students.
Ian Cunningham, the Chief Technical Office of TeachMate, which makes AI tools to help teachers, said:
TeachMateAI already saves teachers over 10+ house of time each week through our AI tools, but we are ambitious about what more we can do to support teachers and schools. The AI education store has the potential to enable us and other developers to produce highly accurate tools for the sector in a much more efficient way, reducing cost, compute and the time it takes us to bring new products to market.
The Department for Education is also today committing to publishing a safety framework on AI products for education, due later this year. Minister Morgan will meet education technology companies before setting out clear expectations for the safety of AI products for education.
Professor Ian Pickup, Pro Vice Chancellor, Students, at The Open University, said:
We’re excited to be a founding strategic partner in this initiative alongside DfE . Since our founding in 1969, we have remained at the forefront of innovation in education. As part of this mission, we have provided free, open-access materials via OpenLearn since 2006, and see the deployment of AI as a means through which even more learners can benefit from the transformative power of education. By making content accessible to new educational technology tools, we foresee a future where learning materials can be best matched to personal needs, where learning tasks can be pitched at the right level for student success, and where students can progress at a pace that is right for them.
The following links open in a new tab
Is this page useful.
Don’t include personal or financial information like your National Insurance number or credit card details.
To help us improve GOV.UK, we’d like to know more about your visit today. Please fill in this survey (opens in a new tab) .
COMMENTS
Learn JavaScript with interactive exercises and quizzes. W3Schools JavaScript Exercises covers topics from basics to advanced. Start coding now!
JavaScript References W3Schools maintains a complete JavaScript reference, including all HTML and browser objects. The reference contains examples for all properties, methods and events, and is continuously updated according to the latest web standards.
JavaScript Exercises, Practice, Solution: JavaScript is a cross-platform, object-oriented scripting language. Inside a host environment, JavaScript can be connected to the objects of its environment to provide programmatic control over them.
Practice 148 exercises in JavaScript. Learn and practice JavaScript by completing 148 exercises that explore different concepts and ideas.
23 Free Websites to Learn JavaScript in 2022. Chaitanya Prabuddha. JavaScript is a programming language that's used for a variety of purposes, including web development, web apps, game development, and more. JavaScript also lets you add dynamic features to web sites that you can't just achieve with HTML and CSS.
Modern JavaScript Tutorial: simple, but detailed explanations with examples and tasks, including: closures, document and events, object oriented programming and more.
Learn JavaScript Learn how to use JavaScript — a powerful and flexible programming language for adding website interactivity.
Write JavaScript for the Web. Welcome to the 100% online school for careers with a future. Get free access to all the features of this course (quizzes, videos, unlimited access to all chapters) by creating an account. So you've learned the basics of JavaScript, and you want to use that knowledge to create dynamic web apps — this is the course ...
What you'll learn Understand how JavaScript is used to react to user events. Write your own JavaScript code to let a person interact with your page. Discuss how JavaScript can introduce accessibility issues.
Looking for JavaScript practice projects? Especially JavaScript projects with source code? Presenting 21 JavaScript Projects for beginners!
JavaScript is a prototype-based language — an object's behaviors are specified by its own properties and its prototype's properties. However, with the addition of classes, the creation of hierarchies of objects and the inheritance of properties and their values are much more in line with other object-oriented languages such as Java. In this section, we will demonstrate how objects can be ...
40 JavaScript Projects for Beginners - Easy Ideas to Get Started Coding JS. The best way to learn a new programming language is to build projects. I have created a list of 40 beginner friendly project tutorials in Vanilla JavaScript, React, and TypeScript. My advice for tutorials would be to watch the video, build the project, break it apart ...
Learn HTML with fun and easy exercises from W3Schools. Test your skills and get instant feedback with the Tryit Editor.
Overview of JavaScript (Week 1 Lecture 1) What is JavaScript? Brief history. Common use-cases. Runtime environments. ECMAScript standards. Overview of language features. Running JavaScript in the browser and at the command line. Debugging JavaScript in the browser.
< >Add the JavaScript code needed to enable auto-complete on this form. Whenever the checkbox is checked, the code should automatically copy the values from Shipping Name and Shipping Zip into the Billing Name and Billing Zip.
SZA shared a screenshot to her Instagram Story on Wednesday, Aug. 28, of an interaction with a fan who desperately needed help with their geometry homework. "Sza I'm failing geometry can you ...
A SZA fan has been struggling in math class, and they turned to the "Snooze" singer for help with their geometry homework. The fan actually received a response to the Instagram DM from SZA ...
Whenever a homework problem asks you to design an algorithm, in addition to giving a clear description of your algorithm (usually, in pseudocode), you should always include an analysis of the running time, and also justification of correctness if correctness is not obvious. If we do not specify what running time to shoot for, faster algorithms ...
SZA's musical talent is well-known, but a fan's recent math homework query exposed her less-than-stellar skills in the school subject. According to Vibe, the fan messaged the SOS singer via DM ...
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window.
Honor and Patrick Jones showcased a new AI feature for the MagicPad 2 that turns your handwritten math notes digital.
AI is being trained up to mark homework for teachers under a new project announced by the Government. The £4 million scheme will see documents including curriculum guidance, lesson plans and ...
AI to mark school homework and plan lessons in £4m project Intervention by artificial intelligence aims to ease burden of teachers, but critics fear breakdown in caring relationships with pupils
Course Information. In this course, you will learn how to use auto-differentiation tools like PyTorch, how to leverage them for basic machine learning algorithms (linear regression, logistic regression, deep nets, k-means clustering), and how to extend them with custom methods to fit your needs.
Late policy: For homework assignments, you will lose 0.5% per late hour (rounded up), with a maximum of 48 late hours per assignment. For example, if you submit HW 1 20 hours late, you lose 10% of points on HW 1 (which is 0.5% of your overall course grade). If you have medical reason for an extension, send both professors a copy of your medical ...
In JavaScript, Objects are King. If you Understand Objects, you Understand JavaScript. Objects are containers for Properties and Methods. Properties are named Values. Methods are Functions stored as Properties. Properties can be primitive values, functions, or even other objects. In JavaScript, almost "everything" is an object.
Use the correct assignment operator that will result in x being 15 (same as x = x + y ). Start the Exercise. Well organized and easy to understand Web building tutorials with lots of examples of how to use HTML, CSS, JavaScript, SQL, Python, PHP, Bootstrap, Java, XML and more.
Teaching standards, guidelines and lesson plans will form a new optimised content store which will train generative AI to make it more reliable for teachers in England; new project will bring ...