New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Temporal Memory Examples (Python) #497
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall it looks good.
Should we remove BacktrackingTM and BacktrackingTMCPP?
__doc__ = """ | ||
A tutorial that shows some features of the Temporal Memory. | ||
|
||
This program has demonstrates some basic properties of the |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
An extra has
.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is a very nice demonstration of TM. 👍
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good spot!
|
||
def testFastLearning(self): | ||
""" | ||
Test with fast learning, make sure PAM allows us to train with fewer |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What is PAM? I assume P is probably Prediction
but I don't know what 'A' and 'M' are.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
PAM stands for "Pay Attention Mode". It was part of the backtracking TM.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ah. I guess I should have remembered that.
if g_options.verbosity > 1: | ||
print("Creating BacktrackingTMCPP instance") | ||
|
||
cppTM = BacktrackingTMCPP(numberOfCols = numCols, cellsPerColumn = 4, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
again...there is no C++ backtracking DM
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
...I mean 'TM'
For issue #216. |
On further review, I'm definitely going to drop the following files from this PR:
Because:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Cool.
Thanks for reviewing this! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good examples, thanks for bringing them in!
One thing, can these be either turned to unit-tests, or ran as a part of testing?
print("") | ||
print("Creating the Temporal Memory") | ||
tm = TM(columnDimensions = (50,), | ||
cellsPerColumn=1, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
TM with 1 cell/col does not really make sense (no higher order learning), unless it's necessary for the example, this should use "normal" number of cells, ie 4,8,...
print("Creating the Temporal Memory") | ||
tm = TM( | ||
columnDimensions = (2048,), | ||
cellsPerColumn=8, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
..oh, ok
Not easily. The primary output of these examples are the text they write and the figures they create. IIRC We already have unit tests which do very similar things as these examples. |
ok, that was my concern, then cease closed 👍 |
I am considering dropping the following files since they are unit tests, not examples. I can add them in a latter PR.