SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1609.01596 · 2016

Direct Feedback Alignment Provides Learning in Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1609.01596.json · badge: /api/ran/1609.01596.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
florian-bacho/dirdfa community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
functional_loss Ran
ran on a synthesized input
florian-bacho/dirdfa/main_fwd_grad.py
code served (permissive licence) · get_code("58b2687e1bd48b65")
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 tuple. 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
import torch.nn.functional as F

torch.manual_seed(0)

# Build a minimal nn.Module that takes params and inputs
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, params, inputs):
        # The function calls fmodel(params, inputs)
        # params is typically a dict of parameter tensors for functional API
        # We'll use functional forward with provided params
        if params is not None:
            # Apply params (weights and biases) to get output
            output = F.linear(inputs, params['weight'], params['bias'])
        else:
            output = self.linear(inputs)
        return output

# Create model and extract parameters
model = SimpleModel()
params = {
    'weight': model.linear.weight.data.clone(),  # shape: (3, 4)
    'bias': model.linear.bias.data.clone()        # shape: (3,)
}

# Create functional model wrapper (identity that just calls forward)
fmodel = lambda params, inputs: F.linear(inputs, params['weight'], params['bias'])

# Create tiny inputs: batch size 2, feature dim 4
inputs = torch.randn(2, 4)

# Create target: batch size 2, class indices (3 classes from output dim)
target = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    'params': params,
    'fmodel': fmodel,
    'inputs': inputs,
    'target': target,
}
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 tuple — a tuple output has no array shape of its own; none is 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
test Not yet run
unverified (harvested, no recorded run)
florian-bacho/dirdfa/main_fwd_grad.py
code served (permissive licence) · get_code("51c09bebc952acfe")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
florian-bacho/dirdfa/main_fwd_grad.py
code served (permissive licence) · get_code("8860f94661609337")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagating the error backward don't have to be symmetric with the weights used for propagation the activation forward. In fact, random feedback weights work evenly well, because the network learns how to make the feedback useful. In this work, the feedback alignment principle is used for training hidden layers more independently from the rest of the network, and from a zero initial condition. The error is propagated through fixed random feedback connections directly from the output layer to each hidden layer. This simple method is able to achieve zero training error even in convolutional networks and very deep networks, completely without error back-propagation. The method is a step towards biologically plausible machine learning because the error signal is almost local, and no symmetric or reciprocal weights are required. Experiments show that the test performance on MNIST and CIFAR is almost as good as those obtained with back-propagation for fully connected networks. If combined with dropout, the method achieves 1.45% error on the permutation invariant MNIST task.

For agents

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

get_harvested_code_for_paper("1609.01596")
get_code_for_paper("1609.01596")
have("1609.01596")

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

curl https://syntology.ai/api/ran/1609.01596.json

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

[![Syntology run record](https://syntology.ai/api/ran/1609.01596.svg)](https://syntology.ai/paper/1609.01596)

Connect an agent — have() is free.