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

Nn stuff #2

Open
wants to merge 178 commits into
base: main
Choose a base branch
from
Open

Nn stuff #2

wants to merge 178 commits into from

Conversation

sagarwal-atg
Copy link

No description provided.

mis0butter added 30 commits April 30, 2023 17:10
@mis0butter
forked from julia_learn. removing everythign that's not GP_june
d9ff1b4
@mis0butter
removed if det(K) == 0 from f_obj in GP_june.jl
2d58516
@mis0butter
updated state plots to accommodate n_vars. working on differentiating…
af9d01e 
… eigenvalues ...
@mis0butter
after talk with dfk, updated obj fn to try using trace of kernel, not…
b453020 
… eigenvalues when det(Ky) = 0
@mis0butter
starting to create more validation plots
8e62960
@mis0butter
created GaussianSINDy repo, renaming project
8c86cf6
@mis0butter
renamed everything to GaussianSINDy
5e2497e
@mis0butter
moved a bunch of functions around. plots are in their own functions, …
6e530d7 
…lorenz_test is much simpler than sindy_gp_est6
@mis0butter
init_params works in repo, plot_option is working
f17b4b0
@mis0butter
ok made a lot of changes ... moved some fns around, they're in utils …
ce3ccab 
…now. created a sandbox_test script. removed double parantheses from functions that aren't being optimized. fixing gaussian progress derivative regression
@mis0butter
following documentation for total variational derivative, testing in …
0f5d96c 
…sandbox
@mis0butter
committing what I have, creating results
8348b63
@mis0butter
thanks very much to Jake for help with evaluating functions of vector…
ac33cb0 
…s of functions and integrating as ODE, committing
@mis0butter
OMG able to dynamically create function of vector of functions, as we…
a381cac 
…ll as integrate
@mis0butter
moved build_dx_fn to inside ode_fns.jl
c07af05
@mis0butter
it works with predator_preygit add .
7d847e6
@mis0butter
got the dumb validate script to work for plotting
bc860fe
@mis0butter
ok validate_data works now with ode_sine, had to restart julia repl why
b28b16a
@mis0butter
have results for predator_prey, plots are looking pretty good actually
b10f934
@mis0butter
fixed legend bug
8cb6a59
@mis0butter
wtf that was so hard. got latex to show up in plot title
ba77d51
@mis0butter
plot margin looks good now
9e89ec6
@mis0butter
committing state that produced predator_prey plot
bc6df31
@mis0butter
fixed a bad typo. using dx_truth_train instead of dx_fd_train
702ed0f
@mis0butter
created metrics for performance. committing what I have now
c90d37f
@mis0butter
put plot of predator_prey into function in utils.jl, starting test/ca…
f07f666 
…r_hardware_test.jl
@mis0butter
created some metrics (just norm) for truth vs sindy vs gpsindy coeffs
fa0ab0c
@mis0butter
building notes in readme. renamed variables to things that make sense…
440235f 
… in predator_prey_test.jl
@mis0butter
updated predator prey coeffs and plot fns
56faea1
@mis0butter
merging after pull
4d8045b
mis0butter and others added 30 commits August 14, 2023 17:30
@mis0butter
updated gp_post arguments
0719f99
@mis0butter
committing current state, need to work on double pendulum fn library
0bf9fa8
@mis0butter
updated monte carlo gpsindy to use gp_post in case 9
089ce8d
@mis0butter
resolved merge conflict
66aea14
@mis0butter
there was remaining git conflict
f4e4bcd
@mis0butter
updated readme with Adam notes, emphasized motivating example
309a425
@mis0butter
added unicycle dynamics and started car_sim_test
00c1e25
@mis0butter
found issue with unicycle dynamics. need to compute more coupled nonl…
4c8e7c1 
…inear terms in fn library
@mis0butter
updated readme with notes. going to update coefficients table for eas…
fb8972b 
…y interpretability
@mis0butter
added nonlinear combinations of sine functions to fn library
d8c5db1
@mis0butter
updated coefficients string vector, size now matches pool_table
8a6475e
@mis0butter
got pretty tables working for coefficients
6d184d1
@mis0butter
added control inputs to nonlinear terms
9b5468a
@mis0butter
updated SINDy_test for optional control input. now can just use one f…
de30ab3 
…unction yay
@mis0butter
using Jake's car data again, understand unicycle dynamics better now
e24d682
@mis0butter
reorganized ode_fns into a folder, split across files
bb541b3
@mis0butter
updated with note, deadline is ICRA SEPT 15git add .
4b96d6e
@mis0butter
implemented linear and angular acceleration quadcopter dynamics, but …
4fe4dd1 
…confused on control kd stuff. downloaded quadcopter data, but need to convert from long/lat to state
@mis0butter
updated pretty_coeffs to only include nonzero rows
4262724
@mis0butter
unicycle dynamics finally work with truth, needed to update control i…
a4ea89c 
…nput to be same in test script and fn
@mis0butter
added data_struct, created ode_train_test, reorganized ode fns
32788d1
@mis0butter
updated data_train push in ode_train_test
527f4be
@mis0butter
updated structs for u, working on Jake's hardware data now. need to v…
5e2224c 
…alidate
@mis0butter
dealt with data rollovers
5ca1a32
@mis0butter
got the x_GP and dx_GP train/test stuff working for Jake's car data
6e14669
@mis0butter
created plot comparing FD vs GP training data for car
f9f3eb9
@mis0butter
that was so confusing ... fixed it build_dx_fn for control input
ef7b103
@mis0butter
CONFIRMED IT WORKS WITH XI_TRUE
d302e1c
@mis0butter
pushing latest code. created test/int_control_test.jl for integrating…
15ad4ad 
… dynamics with control
Added NN training as a baseline
0032d5b
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.
2 participants
@sagarwal-atg @mis0butter