SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.07249 · 2022

Minimizing Control for Credit Assignment with Strong Feedback

arXiv · PDF · Open in the Atlas

Code that ran

8 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 5 failures of our instrument; 10 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2204.07249.json · badge: /api/ran/2204.07249.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mariacer/strong_dfc canonical (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
pennfranc/bio-inspired-continual-learning community (classifier label)
classifier basis not recorded on the link
8 ran · 9 no recorded run
FunctionStatusWhere it lives
LeNetC Ran
ran; our contract draft was wrong, not the code
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/lenet.py
code served (permissive licence) · get_code("8fef921f066b1f46")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned LeNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "out_dim": 10,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LeNet — a LeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LeNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MLP100 Ran
ran on a synthesized input
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/mlp.py
code served (permissive licence) · get_code("67a28e500cf8fce1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MLP. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "activation_override": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MLP — a MLP output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MLP output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MLP20 Ran
ran on a synthesized input
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/mlp.py
code served (permissive licence) · get_code("1df29e9f02681a32")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MLP. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'activation_override': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MLP — a MLP output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MLP output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MLP200 Ran
ran on a synthesized input
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/mlp.py
code served (permissive licence) · get_code("ad5be7c4526b2f74")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MLP. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'activation_override': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MLP — a MLP output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MLP output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ResNet20_cifar Ran
ran; our contract draft was wrong, not the code
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/resnet.py
code served (permissive licence) · get_code("063d93881930a42e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PreActResNet_cifar. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "out_dim": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PreActResNet_cifar — a PreActResNet_cifar output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PreActResNet_cifar output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ResNet56_cifar Ran
ran; our contract draft was wrong, not the code
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/resnet.py
code served (permissive licence) · get_code("a3355598bff4a9c9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PreActResNet_cifar. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "out_dim": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PreActResNet_cifar — a PreActResNet_cifar output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PreActResNet_cifar output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/resnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from amerch/CIFAR100-Training, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_args Ran
ran; our contract draft was wrong, not the code
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/iBatchLearn.py
code served (permissive licence) · get_code("1341f003d9955629")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Namespace. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse
import torch
import numpy as np

torch.manual_seed(0)

# Build the arguments dictionary with valid values for all parameters
ARGS = {
    'argv': [
        '--gpuid', '0',
        '--model_type', 'mlp',
        '--model_name', 'MLP',
        '--force_out_dim', '2',
        '--agent_type', 'default',
        '--agent_name', 'NormalNN',
        '--optimizer', 'SGD',
        '--dataroot', 'data',
        '--dataset', 'MNIST',
        '--n_permutation', '0',
        '--first_split_size', '2',
        '--other_split_size', '2',
        '--workers', '3',
        '--batch_size', '100',
        '--lr', '0.01',
        '--momentum', '0.0',
        '--weight_decay', '0.0',
        '--schedule', '2',
        '--print_freq', '100',
        '--reg_coef', '0.0',
        '--repeat', '1',
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
CIFAR10 Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/clb_dataloaders/base.py
code served (permissive licence) · get_code("af0506c68398edcc")
How it ran

no invocation recorded.

CIFAR100 Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/clb_dataloaders/base.py
code served (permissive licence) · get_code("863446156dbf1191")
How it ran

no invocation recorded.

MNIST Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/clb_dataloaders/base.py
code served (permissive licence) · get_code("9a3033fb697cd22a")
How it ran

no invocation recorded.

NormalNN_reset_optim Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/agents/customization.py
code served (permissive licence) · get_code("a6b5321ddba4e76a")
How it ran

no invocation recorded.

PermutedGen Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/clb_dataloaders/datasetGen.py
code served (permissive licence) · get_code("f9b8caa6279ce116")
How it ran

no invocation recorded.

ResNet110_cifar Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/senet.py
code served (permissive licence) · get_code("38189f93ef69d6ec")
How it ran

no invocation recorded.

SE_ResNet20_cifar Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/senet.py
code served (permissive licence) · get_code("16e2d4177214aebb")
How it ran

no invocation recorded.

SE_ResNet56_cifar Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/models/senet.py
code served (permissive licence) · get_code("e1b5400489e523bc")
How it ran

no invocation recorded.

SplitGen Not yet run
unverified (harvested, no recorded run)
pennfranc/bio-inspired-continual-learning/Continual-Learning-Benchmark/clb_dataloaders/datasetGen.py
code served (permissive licence) · get_code("8c9829ef771c8fe8")
How it ran

no invocation recorded.

loss_function_H Not yet run
unverified (harvested, no recorded run)
mariacer/strong_dfc/dfc/networks/dfc_network_utils.py
code served (permissive licence) · get_code("1c6c7c58e85e4956")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 1 the same month, 1 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
386 dated earlier, 2 the same month, 287 later, 11 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
LeNetC 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
NormalNN_reset_optim 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
PermutedGen 1 other paper
1 dated earlier
2010.04003 (2020-10)
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
ResNet110_cifar 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
ResNet20_cifar 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
ResNet56_cifar 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
SE_ResNet20_cifar 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
SE_ResNet56_cifar 1 other paper
1 dated earlier
2006.11942 (2020-06)
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
SplitGen 1 other paper
1 dated earlier
2010.04003 (2020-10)
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
get_args 1 other paper
1 dated earlier
1810.12488 (2018-10)
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The success of deep learning ignited interest in whether the brain learns hierarchical representations using gradient-based learning. However, current biologically plausible methods for gradient-based credit assignment in deep neural networks need infinitesimally small feedback signals, which is problematic in biologically realistic noisy environments and at odds with experimental evidence in neuroscience showing that top-down feedback can significantly influence neural activity. Building upon deep feedback control (DFC), a recently proposed credit assignment method, we combine strong feedback influences on neural activity with gradient-based learning and show that this naturally leads to a novel view on neural network optimization. Instead of gradually changing the network weights towards configurations with low output loss, weight updates gradually minimize the amount of feedback required from a controller that drives the network to the supervised output label. Moreover, we show that the use of strong feedback in DFC allows learning forward and feedback connections simultaneously, using learning rules fully local in space and time. We complement our theoretical results with experiments on standard computer-vision benchmarks, showing competitive performance to backpropagation as well as robustness to noise. Overall, our work presents a fundamentally novel view of learning as control minimization, while sidestepping biologically unrealistic assumptions.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.07249")
get_code_for_paper("2204.07249")
have("2204.07249")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.07249.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.07249.svg)](https://syntology.ai/paper/2204.07249)

Connect an agent — have() is free.