We lifted 18 functions out of this paper's own repositories and ran 18 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| asikist/nnc | canonical | 18 of 18 |
| Function | Status | Where it lives |
|---|---|---|
| calc_symmetric_interaction_mask | Ran | asikist/nnc/nnc/helpers/torch_utils/graphs.py code served (permissive licence) · get_code("b1997cbc57ca0e24") |
| cca_state_generator | Ran | asikist/nnc/nnc/helpers/data_generators.py code served (permissive licence) · get_code("6a090ebc6bebdbd9") |
| getIfromRGB | Ran | asikist/nnc/nnc/helpers/plot_helper.py code served (permissive licence) · get_code("50b34855bc0d4d70") |
| get_diagonal_elements | Ran | asikist/nnc/nnc/helpers/torch_utils/indexing.py code served (permissive licence) · get_code("88a60f6bc0b7a110") |
| get_max_in_degree | Ran | asikist/nnc/nnc/helpers/torch_utils/graphs.py code served (permissive licence) · get_code("8832c59cce36642c") |
| get_off_diagonal_elements | Ran | asikist/nnc/nnc/helpers/torch_utils/indexing.py code served (permissive licence) · get_code("907742669bc828c5") |
| load_graph | Ran | asikist/nnc/nnc/helpers/graph_helper.py code served (permissive licence) · get_code("e5e8b476ae4b1435") |
| make_norm | Ran | asikist/nnc/nnc/helpers/torch_utils/numerics.py code served (permissive licence) · get_code("0f001098d128b131") |
| multi_unsqueeze | Ran | asikist/nnc/nnc/helpers/torch_utils/indexing.py code served (permissive licence) · get_code("3f6a32e7116b239c") |
| normal_state_generator | Ran | asikist/nnc/nnc/helpers/data_generators.py code served (permissive licence) · get_code("d86018173964e64e") |
| nx_maximum_matching | Ran | asikist/nnc/nnc/helpers/graph_helper.py code served (permissive licence) · get_code("6d7ec7579dbc38e1") |
| read_tensor_from_collection | Ran | asikist/nnc/nnc/helpers/torch_utils/file_helpers.py code served (permissive licence) · get_code("8fb9c9315d7038fb") |
| rms_norm | Ran | asikist/nnc/nnc/helpers/torch_utils/numerics.py code served (permissive licence) · get_code("fb827f0862bcc151") |
| round_to_text | Ran | asikist/nnc/nnc/helpers/plot_helper.py code served (permissive licence) · get_code("f3dfcbe2e0414a05") |
| shape_expectation_failed | Ran | asikist/nnc/nnc/helpers/error_handling.py code served (permissive licence) · get_code("ea62783ddbc2129b") |
| simpson | Ran | asikist/nnc/nnc/helpers/torch_utils/numerics.py code served (permissive licence) · get_code("04f0bdda707bbb55") |
| square_lattice_position | Ran | asikist/nnc/nnc/helpers/graph_helper.py code served (permissive licence) · get_code("8aed6f68b6cdf194") |
| uniform_state_generator | Ran | asikist/nnc/nnc/helpers/data_generators.py code served (permissive licence) · get_code("aafec67fc7f5098b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We study the ability of neural networks to calculate feedback control signals that steer trajectories of continuous time non-linear dynamical systems on graphs, which we represent with neural ordinary differential equations (neural ODEs). To do so, we present a neural-ODE control (NODEC) framework and find that it can learn feedback control signals that drive graph dynamical systems into desired target states. While we use loss functions that do not constrain the control energy, our results show, in accordance with related work, that NODEC produces low energy control signals. Finally, we evaluate the performance and versatility of NODEC against well-known feedback controllers and deep reinforcement learning. We use NODEC to generate feedback controls for systems of more than one thousand coupled, non-linear ODEs that represent epidemic processes and coupled oscillators.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.09773")
get_code_for_paper("2006.09773")
have("2006.09773")
Connect an agent — have() is free.