SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.02509 · 2019

REMIND Your Neural Network to Prevent Catastrophic Forgetting

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 1 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/1910.02509.json · badge: /api/ran/1910.02509.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
tyler-hayes/REMIND canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_accuracies Ran
ran; our contract draft was wrong, not the code
tyler-hayes/REMIND/image_classification_experiments/imagenet_experiment.py
code served (permissive licence) · get_code("7d0f4307baa1803d")
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 numpy as np

torch.manual_seed(0)

# Create a minimal data loader (list of batches with (x, y) tuples)
loader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([1, 0])),
]

# Create a minimal remind model that has a predict method
class MinimalRemind(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 5)
    
    def predict(self, loader, pq):
        # Collect all predictions and labels
        all_probas = []
        all_labels = []
        
        for x, y in loader:
            logits = self.linear(x)
            probas = torch.nn.functional.softmax(logits, dim=1)
            all_probas.append(probas)
            all_labels.append(y)
        
        probas = torch.cat(all_probas, dim=0)
        y_test_init = torch.cat(all_labels, dim=0)
        
        # Return (something, probas, y_test_init)
        return None, probas, y_test_init

remind = MinimalRemind()

# Create a minimal pq object (could be None or a simple stand-in)
pq = None

# Create a minimal utils module with accuracy function
class Utils:
    @staticmethod
    def accuracy(probas, y_test, topk=(1, 5)):
        # Simple accuracy computation
        batch_size = y_test.size(0)
        
        accuracies = []
        for k in topk:
            _, pred = probas.topk(k, 1, True, True)
            pred = pred.t()
            correct = pred.eq(y_test.view(1, -1).expand_as(pred))
            acc = correct[:k].reshape(-1).float().sum(0, keepdim=True).mul_(100.0 / batch_size)
            accuracies.append(acc.item())
        
        return tuple(accuracies)

utils = Utils()

# Inject utils into the module namespace (or mock it directly)
import sys
module = sys.modules[__name__]
module.utils = utils

ARGS = {
    "loader": loader,
    "remind": remind,
    "pq": pq,
}
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 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
randint Ran
ran; our contract draft was wrong, not the code
tyler-hayes/REMIND/image_classification_experiments/REMINDModel.py
code served (permissive licence) · get_code("1b8cb9c8dfce51c5")
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) and returned dict_keys. 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

# Set random seed for reproducibility
np.random.seed(0)

# Define arguments for the randint function
ARGS = {
    "max_val": 100,
    "num_samples": 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict_keys — a dict_keys output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict_keys 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
get_data_loader Not yet run
unverified (harvested, no recorded run)
tyler-hayes/REMIND/image_classification_experiments/imagenet_experiment.py
code served (permissive licence) · get_code("f0a5673d31a458ed")
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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
randint 1 other paper
1 later
2303.10725 (2023-03)
SIESTA: Efficient Online Continual Learning with Sleep

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

People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the brain consolidates memory. Replay involves fine-tuning a network on a mixture of new and old instances. While there is neuroscientific evidence that the brain replays compressed memories, existing methods for convolutional networks replay raw images. Here, we propose REMIND, a brain-inspired approach that enables efficient replay with compressed representations. REMIND is trained in an online manner, meaning it learns one example at a time, which is closer to how humans learn. Under the same constraints, REMIND outperforms other methods for incremental class learning on the ImageNet ILSVRC-2012 dataset. We probe REMIND's robustness to data ordering schemes known to induce catastrophic forgetting. We demonstrate REMIND's generality by pioneering online learning for Visual Question Answering (VQA).

For agents

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

get_harvested_code_for_paper("1910.02509")
get_code_for_paper("1910.02509")
have("1910.02509")

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

curl https://syntology.ai/api/ran/1910.02509.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.02509.svg)](https://syntology.ai/paper/1910.02509)

Connect an agent — have() is free.