Brainhack brainstorming (tomorrow)

Engineering
1

There’s a brain-related hackathon in EPFL’s Campus Biotech in Geneva, November 7-9: brainhack.ch
We’re going to brainstorm ( :stuck_out_tongue: ) for a project tomorrow and I wonder if we can source any ideas from the community here. All results are open source!

The hackathon has a broad scope. Although originally envisaged as related to brain imaging in particular, any brain-related project will do. We’re thinking to move along the lines of picking some open dataset and using it to achieve an interesting result in 2 days. My exploration will start at Kaggle.

~ Do you think we could examine an HTM-related question in this context?
~ Do you have any pointers to datasets we might be able to use for that?

3 Likes
2

2 days is quite a short time! Even if you can utilize the full 48 hours.

One thing I haven’t done but would like to try is since we now have Grid Cells can Grid Cell Encoders. We should be able to replace the old GeoLocation Encoder with a GC Encoder. We should see a boost in anomaly detection capabilities in geo location tracking.

Context:


1 Like
3

After listening to the Affordance Competition Hypothesis, I was wondering if it is possible to build a mind mapping algorithm based on those. To be able to build the maps to fall into those classifications. I have been thinking about this since looking at Ben Goertzel’s OpenCog project. I already put in a preemptive submission at the hackathon called MemoreX, a pun on Vannevar Bush’s CIA project.

2 Likes
4

Thanks a lot for your suggestions!
We went around a few different directions and ended up proposing this project:

Through your eyes – reconstruct visual stimuli from EEG data

Inspired by recent successes in reconstructing images people see with their eyes from their fMRI recordings (thanks @Bitking!)

and claims of proof-of-concept results with EEG instead, we thought it would make for a very interesting and attractive hackathon effort to try and corroborate such claims. The scope is likely much more than we can afford to complete in 2 days, but we chose it rather aesthetically: it’s exciting!
We hope to attract an EEG experimentalist [1], as our core team has ML, software engineering and medical expertise. If not, we’ll pivot to the fMRI paper and try something new with their model and data, both of which are public.

[1] We can also work on open EEG datasets, but so far we haven’t found anything relevant to our questions.

1 Like