SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.16981 · ICML · 2020

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

Yoshua Bengio, Michael Mozer, Anirudh Goyal, Sarthak Mittal, Alex Lamb, Vikram Voleti, Murray Shanahan, Guillaume Lajoie

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2006.16981.json · badge: /api/ran/2006.16981.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
sarthmit/BRIMs canonical (classifier label)
classifier basis: classifier_2025
3 ran · 2 no recorded run
FunctionStatusWhere it lives
mnist_prep Ran
ran; our contract draft was wrong, not the code
sarthmit/BRIMs/CIFAR10/train_cifar.py
pointer only (licence: NONE) · get_code("c19191922d6d0a4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sarthmit/BRIMs 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.

mnist_prep Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sarthmit/BRIMs/MNIST/train_mnist.py
pointer only (licence: NONE) · get_code("e9e25e185572a0bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sarthmit/BRIMs 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.

multimnist_prep Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sarthmit/BRIMs/MNIST/train_mnist.py
pointer only (licence: NONE) · get_code("ca909a845b0ab2d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sarthmit/BRIMs 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.

repackage_hidden Not yet run
unverified (harvested, no recorded run)
sarthmit/BRIMs/CIFAR10/train_cifar.py
pointer only (licence: NONE) · get_code("9e50bd9c4161128d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sarthmit/BRIMs 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. No invocation recorded.

repackage_hidden Not yet run
unverified (harvested, no recorded run)
sarthmit/BRIMs/MNIST/train_mnist.py
pointer only (licence: NONE) · get_code("0ed7de278461e386")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sarthmit/BRIMs 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. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what's directly observed through sensation. Topdown signals consist of beliefs and expectations based on past experience and short-term memory, eg. how the phrase 'peanut butter and ...' will be completed. The optimal combination of bottomup and top-down information remains an open question, but the manner of combination must be dynamic and both context and task dependent. To effectively utilize the wealth of potential topdown information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow. We explore deep recurrent neural net architectures in which bottom-up and topdown signals are dynamically combined using attention. Modularity of the architecture further restricts the sharing and communication of information. Together, attention and modularity direct information flow, which leads to reliable performance improvements in perceptual and language tasks, and also improves robustness to distractions and noisy data. We demonstrate on a variety of benchmarks in language modeling, sequential image classification, video prediction and reinforcement learning that the bidirectional information flow improves results over strong baselines.

For agents

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

get_harvested_code_for_paper("2006.16981")
get_code_for_paper("2006.16981")
have("2006.16981")

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

curl https://syntology.ai/api/ran/2006.16981.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.16981.svg)](https://syntology.ai/paper/2006.16981)

Connect an agent — have() is free.