Possible Project Ideas
- Extend and expand on your midterm project using NEAT.
- Apply any of the systems we discussed this semester to an adaptive
robot task. One option is to try to reproduce an experiment we read
about.
- Intelligent Adaptive Curiosity (IAC)
- Growing Neural Gas (GNG)
- Category-Based Intrinsic Moitvation (CBIM which combines GNG with
IAC)
- Self-Organizaing Distinctive state Abstraction (SODA)
- Reinforcement learning (Q-learning)
- Try improving on a system we discussed:
- Reconfigure IAC by replacing the experts within each region with
a monolithic expert (as described in the footnote at the bottom of
page 269 of the IAC paper). The monolithic expert could be a
recurrent neural network allowing IAC to learn dependencies in time.
- Invent your own adaptive robotics approach using aspects of any
of the systems we've discussed.
- Take an idea from a previous CS81 project and expand on it:
Proposal, Due April 6 at start of class
Your project proposal should be at least two pages long. It
should include a clear description of:
-
The adaptive method you will be testing.
-
The environment and robot you will use in the experiment.
-
Your hypothesis and expected outcome.
-
How you will analyze the results to demonstrate that some kind of
development has actually occurred.
Checkpoint demonstraction, In-class April 13
Your experiment not need to be completed at this point, but be
prepared to describe the developmental architecture you will use, your
planned experiment, and your hypotheses. You should plan to speak for
7-8 minutes.
Presentation, In-class April 20, 22, 27, or 29
You should plan to give a 25 minute presentation about your project.
Each group will be assigned a date to speak during the last two weeks
of class. It may be the case that you are still running experiments at
this point. However, you should have some preliminary results to
report. If it is a team project, then each team member should speak
for an equal portion of the time. Your must use slides of some
kind. Options for displaying slides include: openoffice,
powerpoint, and acroread for pdf documents.
You should follow these
guidelines (put together by Tia Newhall) when creating your talk.
Paper, Due by noon May 14
Your paper should include the following:
- A short abstract of 200 to 300 words summarizing your findings.
- An introduction that contrasts your study with other related
work. Find and read at least three articles related to your
experiment and discuss these papers here. Read about how to properly
cite related work.
- A detailed description of your experiments. There should be
enough information so that someone could reproduce your experiments.
- An explanation of the results. Use figures and tables where
appropriate.
- A discussion of the significance of the results.
- A bibliography.
Your grade will not be based on whether or not your
experiment succeeds. Negative results are also useful. Your grade
will be based on the design and execution of the experiment as well as
the thoroughness and readability of the paper. You do not need to
turn in any programs. Email me a pdf version of your
paper.