Posted by: ahamer 5 years, 11 months ago

(0 comments)

So there's been a content and research gap round these parts because a bunch of stuff happened.

And moving right along...

I decided to put some structure in place to ensure that I make progress and actually finish.

1) Every other week meeting with adviser w/ co-chair as optional

Treat these like standup, albeit with a much lower cadence. What did, blockers, what do next.

2) Keep records of these meetings

Jump through school hoops of activity + easy reference for other stuff

3) Keep a research log

Read a paper? Write a log. Run a sim? Write a log. Crazy idea that just might work? Write a log.

3a) Write recaps of research log, send to standup attendees day before

So we can skip context building in the meeting.

4) Build a project plan with some capacity for failure.

Get Hurewitz et al 2006 performance from images. See if that ports to word problems as input. Try to get cardinals from there.

5) Identify uncertainty in the plan - mitigate it or eliminate it ASAP

Timelines are fuzzy, so focusing on making sure I can get a sim of Hurewitz et al 2006 working with hand-constructed inputs and then work back to image input. Use this to feel out how much I need to give the model - how much heavy lifting does the image preprocessor need to do? Can I rely on the Gallistel pulses stuff as a fallback if the image preprocessor is too hard?

6) Make sure we're jumping through the right process hoops

Write annual progress report, review in ~2 weeks (8w before deadline). This doc should just be a project plan for the rest.

7) Set up a lit summary

Write 1 page reviews of everything I read that's relevant. This goes in research log, but gets tagged for lit review. Paper, basic results.

8) Start operationalizing the plan.

Lay out the hand-labeled stuff above as sim 1. Write it up as such. Work out the sim/behavioral task mapping for the rest of the papers.

9) Figure out how to pay for it.

You gotta deal with the stuff that knocked you off the wagon or it's gonna be a long, burnt out journey.

• ← Focus
• Human-like generalization in a machine through predicate learning →