Completed Project

Requirements

You must:

complete peer- and self-evaluations (on gradescope),
address my comments (see this video showing how to use Hypothesis),
add an abstract at the beginning of your report (see How to write a good abstract for a scientific paper or conference presentation), and
record a 7 to 15 minute presentation (either embed/link it on your web-page (e.g., from Vimeo or YouTube) or give me a link to an unlisted video (e.g., host on Vimeo or YouTube) on Gradescope when you submit your final webpage link).

The due date for seniors cannot be extended.

The report follows a sensible outline (note, you should write using whatever outline is most natural for your paper and you do not need to stick to the introduction->background->methods->discussion format)
The report addresses concerns listed on the first draft.
The report was clear and provided a coherent narrative.
The project involves neural networks and/or neural network ethics.
- If the project does not directly include any ethical implications, then the project must include a separate, standalone ethics discussion on a topic of your choosing.
The project is related to the group project proposal and updates.
The project contains at least one of the following elements:
- a survey or comparison of different techniques, models, or hyperparameters,
- creation of a new concept or idea,
- a complete application with some form of user interface, and
- a thorough discussion on an ethics topic.

Here are the concepts on which I will provide feedback.

If you are looking for additional information, I recommend taking a look at these more formal/complete rubrics.

Some suggested tools for creating and editing videos. You may use whatever you’d like.

I do not have a preference for your presentation format. Common methods include:
- Slides (including Pecha Kucha)
- Live typing (similar content to slides) (example)
- Live diagramming (for example on a whiteboard)
- Live demos (this one is harder to do in our setting)
The Think Fast, Talk Smart: The Podcast (here is a specific recommendation: Mindset Matters: How to Embrace the Benefits of Stress) is a good listen. You might as well start week 1!
This is not a professional research talk. I would like to be informed, but it is also OK for you to also entertain.
It does not need to follow the same format/flow as the article(s) you present. A presentation is just an advertisement for the article.
Don’t memorize your “script,” but you can memorize transitions. If you over rehearse it will be difficult to recover from a mistake and it will come across as robotic.
Know how are you being “evaluated.” Is this a job talk (evaluated on ability to contribute to team)? Graduation keynote (people want to be inspired and enjoy the process)? For a grade (what is the rubric)? Informative (make sure you are credible)?
Presentations can come in any format. Here are a couple of great descriptions of how to craft a compelling presentation:
- Simon Peyton Jones’ advice on How to give a great research talk.
- How to Make a Pecha Kucha - YouTube

Most presentations will follow this structure/outline:

Introduction
- Have a solid initial prompt (question, story, bold statement, statistic, quiz, benefit)
- Tell the audience why should they should care
- Tell the audience what will they learn
- Provide some form of preview or demo of final result
Body
- Provide the research context (some topics appear in many fields, but are discussed differently)
- Discuss the approach and how is it novel or of interest
- Show results and the corresponding experiments to show credibility
Ending
- Summarize the key contributions
- Give a call to action
- Acknowledge contributors
- Prompt for questions and feedback