Optimized Memristive Reservoir using CuPy #49
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…and added a return parameter to fetch_data that allows to run simulate on input values originally cut, allowing for more accurate Memory capacity measurement
…d with earlier version
…al as per Molter 2014 code
…lemented multitasking class and updateNodes method for easier changing of nodes between different in/out runs
… decided as a ratio of NMSS rather than normally distributed around a mean. Also fixed updateG since Nb had bgu hwere it was being updated to be higher that NMSS or less than 0
This reverts commit 5cb19bd.
… Removed some tracking print statements
… data in a pandas series, moved simulate history matrices out from gpu to allow for more sapce in gpu (allows for more timesteps and time lag before gpu runs out of space)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Optimized the computation time of Memristive reservoir
-Used CuPy to move computation to GPU
-Added install steps for CUDA and CuPy as a txt file since, couldn't figure out how to add to dependancies (CUDA too complex)
-Added example5.sim to demonstrate a fully optimized using parallel computation and the CuPy class of memristive reservoir
-Retained the input that's cut off during fetch_data and showed how it can be simulated in example5
-Did some bug fixing and extra documentation