SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.08006 · 2018

Bidirectional Learning for Robust Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/1805.08006.json · badge: /api/ran/1805.08006.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
sidneyp/bidirectional canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
f Ran
ran, honoured the contract we drafted
sidneyp/bidirectional/bidirectional_proof.py
code served (permissive licence) · get_code("54383f7845419e7a")
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 Tensor, ndim 2, dtype family int, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function f(v) takes a single argument v and performs a comparison v > 0,
# then multiplies by 1 (which keeps it as a tensor or array of bools/ints).
# The argument should be a tensor or array-like object that supports comparison.

v = torch.randn(2, 4)

ARGS = {
    "v": v
}
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 Tensor, ndim 2, dtype family int, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_data_csv_file Ran
ran, honoured the contract we drafted
sidneyp/bidirectional/utils_csv.py
code served (permissive licence) · get_code("8c2a75875b5ed499")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 csv
import tempfile
import os

# Create a temporary CSV file with test data
temp_dir = tempfile.mkdtemp()
csv_file_path = os.path.join(temp_dir, "test_data.csv")

# Write test data to CSV
with open(csv_file_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow([1, 0.5, 0.3, 0.7, 42])
    writer.writerow([2, 0.6, 0.4, 0.8, 43])
    writer.writerow([3, 0.7, 0.5, 0.9, 44])

ARGS = {
    "data_file": csv_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
print_best Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sidneyp/bidirectional/utils_csv.py
code served (permissive licence) · get_code("191228141ee6f849")
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 str. 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 numpy as np
import tempfile
import os

# Create a temporary file for output
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
fileout = temp_file.name
temp_file.close()

# Create sample data arrays
n_iterations = 10

# accu_data: (x, accu_test, accu_random, accu_adv, counter)
x = np.arange(n_iterations)
accu_test = np.random.rand(n_iterations)
accu_random = np.random.rand(n_iterations)
accu_adv = np.random.rand(n_iterations)
counter = np.arange(n_iterations)

accu_data = (x, accu_test, accu_random, accu_adv, counter)

# sigmoid_data: (_, sigmoid_test, sigmoid_random, sigmoid_adv)
# The function accesses indices [1], [2], [3], so index 0 can be None
sigmoid_test = np.random.rand(n_iterations)
sigmoid_random = np.random.rand(n_iterations)
sigmoid_adv = np.random.rand(n_iterations)

sigmoid_data = (None, sigmoid_test, sigmoid_random, sigmoid_adv)

# softmax_data: (_, softmax_test, softmax_random, softmax_adv)
# The function accesses indices [1], [2], [3], so index 0 can be None
softmax_test = np.random.rand(n_iterations)
softmax_random = np.random.rand(n_iterations)
softmax_adv = np.random.rand(n_iterations)

softmax_data = (None, softmax_test, softmax_random, softmax_adv)

ARGS = {
    'accu_data': accu_data,
    'sigmoid_data': sigmoid_data,
    'softmax_data': softmax_data,
    'fileout': fileout
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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

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

A multilayer perceptron can behave as a generative classifier by applying bidirectional learning (BL). It consists of training an undirected neural network to map input to output and vice-versa; therefore it can produce a classifier in one direction, and a generator in the opposite direction for the same data. The learning process of BL tries to reproduce the neuroplasticity stated in Hebbian theory using only backward propagation of errors. In this paper, two novel learning techniques are introduced which use BL for improving robustness to white noise static and adversarial examples. The first method is bidirectional propagation of errors, which the error propagation occurs in backward and forward directions. Motivated by the fact that its generative model receives as input a constant vector per class, we introduce as a second method the hybrid adversarial networks (HAN). Its generative model receives a random vector as input and its training is based on generative adversarial networks (GAN). To assess the performance of BL, we perform experiments using several architectures with fully and convolutional layers, with and without bias. Experimental results show that both methods improve robustness to white noise static and adversarial examples, and even increase accuracy, but have different behavior depending on the architecture and task, being more beneficial to use the one or the other. Nevertheless, HAN using a convolutional architecture with batch normalization presents outstanding robustness, reaching state-of-the-art accuracy on adversarial examples of hand-written digits.

For agents

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

get_harvested_code_for_paper("1805.08006")
get_code_for_paper("1805.08006")
have("1805.08006")

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

curl https://syntology.ai/api/ran/1805.08006.json

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

[![Syntology run record](https://syntology.ai/api/ran/1805.08006.svg)](https://syntology.ai/paper/1805.08006)

Connect an agent — have() is free.