Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Make trainable_engine_t independent #65

Merged
merged 12 commits into from
Jun 30, 2023
Merged

Make trainable_engine_t independent #65

merged 12 commits into from
Jun 30, 2023

Conversation

rouson
Copy link
Contributor

@rouson rouson commented Jun 30, 2023

Witih this PR, trainable_engine_t no longer extends inference_engine_t.

rouson added 12 commits June 27, 2023 13:57
@rouson
feat(trainable_engine): encapsulate padded w, b, n
f4840d3 
This commit defines new trainable_engine_t components that store
the padded arrays used in the new deep network training algorithm
to store the weights (w), biaes (b), and layer widths (n).  These
components are redundant: the same information stored in updadded
arrays in the parent inference_engine_t type.  If it turns out
that inference performs comparably or better than with the
unpadded data structures -- despite the indirect addressing
required with the padded forms -- then trainable_engine_t can be
refactored to no longer extend inference_engine_t.
@rouson
test(trainable_engine): infer with padded arrays
d30fda1 
This commit switches the AND-gate test to use the recently defined
trainable_engine_t padded-array components for inference.
@rouson
Merge branch 'main' into trainable-engine-inference
42e3800
@rouson
test(train): random initial w,b shortens runtime
f8c0669
@rouson
fix(train): rm mistaken re-initialization of w, b
fc819a8
@rouson
refac(train): eliminate unneeded intermediate def
4fb6113
@rouson
test(train): skewed input reduces test runtime
508a671
@rouson
test(train): OR test, print_truth_table subroutine
77d04f2
@rouson
test(train): XOR test, randomized weights, biases
2ea0b1f
@rouson
chore: rm training examples
7ba87b1
@rouson
feat(trainable_engine): no extend inference_engine
48a6680
@rouson
test(trainable_engine): more robust num iterations
7995aca 
This commit sets the number of training iterations in each unit
test so that the tests pass repeatedly even when the random_init
subroutine's "repeatable" argument is set to .false. in test/main.f90.
@rouson rouson merged commit 5b8366e into main Jun 30, 2023
4 checks passed
@rouson rouson deleted the trainable-engine-inference branch June 30, 2023 12:39
@rouson rouson restored the trainable-engine-inference branch July 1, 2023 14:43
@rouson rouson deleted the trainable-engine-inference branch July 1, 2023 14:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@rouson