CS294S is a research project course to explore how machine learning can revolutionize consumers' software experience. Students are invited to do quarter-long projects to answer questions such as those listed below or propose their own topics
CS294S is a cross-disciplinary research project course, designed to help students with their first research experience, emphasizing individual mentorship and learning through projects, rather than lecture-style learning. Students interested in AI, HCI, or programming systems, who have taken at least two computer science courses are welcome to attend.
Students, in groups of 1 to 3, can propose their projects or choose among suggested topics. Available to the students is the open-source Almond virtual assistant infrastructure, which can be used to prototype a natural language interface in just one day.
Students are required to come to campus for this course, where in-class participation and after-class project meetings are required. You can take this course multiple times for credit. CS 294S can be taken to fulfill the CS 194 requirement. Please sign up for CS 294W if you wish to fulfill your writing requirement as well.
We wish to explore if end-user programming is possible. Can software be tailored, or even created, using natural language according to individuals' needs and interests?
Virtual assistants are the first of such systems, giving users a uniform personalized natural-language based interface. Can we improve their accuracy with personalization? Can we enable non-technical individuals to automate mundane tasks by scripting their virtual assistant using natural language, possibly with the help of examples? We imagine in the future, knowledge workers like loan officers or stock traders will train their own professional virtual assistants.
Today, consumers have little choice other than Facebook to share information easily with each other. Sharing is technically difficult because of access control, which is notoriously user-unfriendly. Can machine learning revolutionize sharing by giving users a natural interface?
In the future, we will see a combination of language and graphical user interfaces in every app. How do we make the best of both worlds, easily? Can ideas like style transfer be applied to make our apps dramatically more aesthetically pleasing?
We imagine in the future, there will be a ThingNet, a neural network that understands how all of the digital world operates. How do we get there?
The course meets Tuesday and Thursday, from 10:30 AM to 11:50 AM in Gates 100.
This schedule is tentative and subject to change. Please pay attention to emails sent to the student list.
|Tue April 3||Overview of the course (slides).|
|Thu April 5||Intro + brainstorming + demo (slides). Homework 1 released.|
|Tue April 10||Project discussions|
|Thu April 12||More ideas + in-class discussions. Project proposal meeting signup.|
|Tue April 17||Mini hackathon. Homework 1 due.|
|Thu April 19||Project proposal.
|Tue April 24||Project proposal.
|Thu April 26||Project proposal|
|Tue May 1||Tutorial: semantic parsing|
|Thu May 3||Guest lecture: data programming|
|Tue May 8||Student-led discussion|
|Thu May 10||Student-led discussion|
|Tue May 15||Mini hackathon / work session|
|Thu May 17||Student-led discussion|
|Tue May 22||Student-led discussion|
|Thu May 24||Student-led discussion|
|Tue May 29||Final project discussion|
|Thu May 31||Final project discussion|
|Tue June 5||Final project discussion|
|Mon June 11: (1:30-3:15 pm)||Final project demo and poster session (during the scheduled final exam period)|
|Tue June 12||Final report due|
10 minutes + 10 minutes for questions and discussion. Your proposal should include:
15 minutes + 3 minutes for questions. Your presentation should include:
There is no page limit (minimum or maximum), but CS294W students must have substantial writing. Your report should include:
Office hours: by appointment
Office hours: Wednesday and Friday, 2 PM to 4 PM (Gates 407)