ECS 170 Project Presentation

Presentation Format:

1. Duration: Each group will have a total of 11 minutes for their presentation.

   • Presentation Time: ~9 minutes. Walk the audience through your project, its objectives, methods, results, implications, and what you learned.
   • Q&A Session: ~2 minutes. This time is set aside for questions, feedback, and discussion with the audience.

2. Division of Time: Ensure that the presentation time is distributed approximately evenly among your group members.

3. Content Structure: Here's a suggested flow to structure your presentation:

   • Introduction: Briefly introduce your project and its objectives.
   • Background: Recall any concepts that the audience should remember to be able to understand your project.
   • Methodology: Discuss the AI technologies and methods you applied, the challenges you faced, and how you overcame them.
   • Results: Present the outcomes of your project, supplemented with visual aids - a slideshow, and optionally a live demonstration.
   • Discussion: Reflect on the implications of your findings, any limitations, and potential future directions or improvements.
   • Conclusion: Sum up the main points and the significance of your project.

4. Collaboration: An effective presentation will have group members primarily presenting the segments they contributed most to. However, during the Q&A, any member could be posed a question about any part of the project.

5. Location: Presentations will be held over Zoom (or another video conferencing solution). If you would prefer an in-person presentation, please send me an email well in advance.

6. Time: Presentations will take place during the last week of class - keep an eye on Canvas for announcement with a link to sign up for a presentation slot.

7. Audience: The audience for the presentations will be myself and one TA. If you're feeling confident, feel free to invite your classmates.

Preparation Tips:

1. Rehearse: Practice your presentation multiple times to refine your flow, ensure you're within the time limit, and bolster your confidence.

2. Visual Aids: Use slides or other visual aids to make your presentation engaging and illustrative. Specifically, include complete figures.

   Complete figures have:

   • Ticks (if applicable)
   • Tick labels (if applicable)
   • Axis labels
   • Titles
   • Legends with clear legend labels
   • Highlights (optional)

   The mapping between marks on the figure and concepts in the viewer's mind should be made clear by:

   • The figure itself, especially axis labels
   • Your description of the figure

   I highly recommend that you learn about the "grammar of graphics" if you haven't already. Try searching YouTube for videos by Tamara Munzer.

3. Engage Your Audience: Aim to communicate what you did in an accessible way. The goal is clarity and understanding.

4. Anticipate Questions: Think about potential questions you might be asked and prepare answers. This will make the Q&A smoother and more productive.

5. Squint test your slides: Put your laptop on a table in a small room and stand across the room. Can you read the slides? If not, the text may be too small. Beware:

• Networks with lots of nodes and edges
• Pairwise correlation matrices with lots of labels
• Other

6. Avoid code screenshots unless they are very succint (10 lines or less). Consider alternative presentation techniques for your algorithm, like high-level pseudocode or a flowchart. In short, code screenshots are not as informative as you might think. Consider how long it takes you to read source code in a library you are unfamiliar with.

Good to present some things in the right amount of detail vs. everything in not enough detail. Choose wisely.

What should you NOT present?

Avoid "Fluff"

• Definitions of AI and machine learning
• Long definitions of "what is an API". Assume most Upper div CS majors have learned this?
• Too many takeaways/summaries
  • One discussion and conclusion slide is ok!
  • Discussion, Takeaways, Key Takeaways, Final Takeaways, Conclusion, Last Notes is far too much!

Avoid low-information content

• Code screenshots of >5-10 lines. Use code screenshots very judiciously or not at all.
• Long lists of uninterpretable column names

What should you do if you're short on time?

If you need to condense your presentation, you can trim:

• Deep technical details
• Intro slides like "what is machine learning"
• Vague conclusions

Evaluation Criteria: Your presentation will be evaluated on:

• Content depth and clarity.
• Structure and logical flow of the presentation.
• Engagement and communication skills.
• Ability to address questions and feedback constructively.
• Collaboration and equitable contribution from all group members.

Questions

Here are some typical questions you might anticipate for your presentation:

• Is there a theoretical upper limit on performance for this task? What is it? How is it derived?
• Is there a theoretical lower limit on performance for this task? What is it? How is it derived?
• Are your results sensitive to your choice of hyperparameters? How sensitive? How do you know?
• What inputs to the system influence its behavior the most? The least? How do you know?
• How does your system compare to weak baselines for this task? Strong baselines?

Low-priority tips

7. Don't mix light-mode slides and dark-mode screenshots
8. Axis labels on figures are often too small for presentation by default. You can find this out by squint testing your slides. Configure matplotlib, seaborn, altair, etc. (whatever library you use for visualization) to increase the font size.
9. Clarify what resources you started with and what you added on top.
10. If you have Night Light, Redshift, or another screen color temperature app on the laptop you use for presentation, turn it off during the presentation
11. Don't just throw an AI-generated figure in the presentation because this is an AI class. Include informative figures.
12. Neural network training curves are usualy informative if validation and training metrics are sampled more often than once per epoch. A lot can happen in an epoch!
13. If you include a demo video, consider showing it at 2x speed or editing non-informative segments
14. Round long decimals
15. Don't just copy paste the sklearn classification report, it could be much more readable.

Good Luck!

Presentation Rubric

Category	Criteria	Exceptional (5)	Good (4)	Satisfactory (3)	Needs Improvement (2)
1. Content	a. Relevance and Depth	Topic is highly relevant to the course; includes thorough evaluation (if applicable) and comparison to baselines (if applicable); demonstrates deep understanding	Topic is relevant to the course; includes reasonable evaluation; compares to baselines or explains why baselines are unavailable	Topic is somewhat relevant; evaluation is present but shallow	Topic relevance is unclear; little to no evaluation of results
	b. Technical Clarity	Clear rationale for all technical choices (models, algorithms, problem framing); methodology is explained at appropriate level of detail	Rationale provided for most technical choices; methodology is mostly clear	Some technical choices explained; methodology could be clearer	Technical choices not justified; methodology is confusing or missing
2. Structure	a. Logical Flow	Presentation has clear, logical progression; transitions between sections are smooth; easy to follow from start to finish	Presentation is generally well-organized; most transitions are clear	Some organizational issues; flow is occasionally hard to follow	Presentation is disorganized or difficult to follow
	b. Avoiding Low-Information Content	No fluff (generic AI definitions, excessive summaries); no code screenshots >10 lines; all content is purposeful	Minimal fluff; code screenshots kept short; most content is purposeful	Some unnecessary content or overly long code screenshots	Significant fluff, generic definitions, or excessive code screenshots
3. Engagement	a. Motivation and Interest	Compelling case for why topic is important; real-world use case clearly articulated; audience is engaged throughout	Good explanation of topic importance; some real-world context provided	Some attempt to motivate the topic; limited real-world connection	No clear motivation for why topic matters
	b. Delivery	Presenters speak clearly, confidently, and at appropriate pace; maintains audience attention	Presenters speak clearly; minor issues with pace or confidence	Some difficulty hearing or following presenters; uneven delivery	Presenters are difficult to hear or understand; poor delivery
4. Visual Aids	a. Figure Completeness	All figures have axis labels, titles, legends with clear labels, and appropriate tick marks; encoding is explained verbally or in text	Most figures have complete labels; encoding is mostly clear	Some figures missing labels or legends; encoding sometimes unclear	Figures are incomplete or unexplained; encoding is confusing
	b. Figure Quantity	Several well-chosen, informative figures that enhance understanding	1-2 figures, or several figures that are less informative	Only 1 figure, or figures that add little value	No figures, or figures that detract from the presentation
	c. Slide Readability	Slides are easy to read from a distance; not text-heavy; visuals enhance understanding	Slides are mostly readable; some text-heavy slides but manageable	Some slides difficult to read; too much text in places	Slides are hard to read; overly text-heavy throughout
5. Time & Pacing	a. Balanced Speaking Time	Speaking time is balanced among all presenters	Speaking time is slightly imbalanced but reasonable	Speaking time is noticeably imbalanced	Speaking time is severely imbalanced
	b. Time Limits	Presentation finishes within time limits	Presentation slightly over/under time	Presentation moderately over/under time	Presentation significantly over/under time
	c. Q&A Time	Leaves appropriate room (~2 mins) for Q&A	Leaves some room for Q&A (1-2 mins)	Minimal time for Q&A	No time left for Q&A (unless due to technical difficulties)
	d. Pacing	Appropriate pacing throughout; not rushed or dragging	Pacing is mostly good with minor issues	Pacing is uneven; some sections rushed or slow	Pacing is poor; presentation feels rushed or drags significantly
6. Q&A	Handling Questions	Answers questions thoughtfully and accurately; demonstrates deep understanding of the project; handles unexpected questions gracefully	Answers most questions adequately; shows good understanding of the project	Answers some questions but struggles with others; understanding seems surface-level	Unable to answer questions or provides incorrect/confused responses

Note: Each criterion is scored on a scale of 2-5. Technical difficulties or extenuating circumstances will be taken into account where applicable.