SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.09303 · ICLR · 2024

Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag

Felix Wichmann, Lukas Huber, Fred Mast

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 4 failures of our instrument; 2 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/2402.09303.json · badge: /api/ran/2402.09303.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
wichmann-lab/supervised-learning-dynamics canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy_per_run_an_epoch Ran
ran, honoured the contract we drafted
wichmann-lab/supervised-learning-dynamics/analysis/utils/analyses.py
pointer only (licence: NONE) · get_code("ca088e81f1b522c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

add_row_to_dataframe Ran
ran; our contract draft was wrong, not the code
wichmann-lab/supervised-learning-dynamics/analysis/utils/helper.py
pointer only (licence: NONE) · get_code("ec5d54cf6dd0128e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

calc_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wichmann-lab/supervised-learning-dynamics/analysis/utils/analyses.py
pointer only (licence: NONE) · get_code("b15d046ac1514495")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

calculate_accuracy_np Ran
ran, honoured the contract we drafted
wichmann-lab/supervised-learning-dynamics/analysis/utils/analyses.py
pointer only (licence: NONE) · get_code("a6c0530123b908e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

dir_up Ran
ran; our contract draft was wrong, not the code
wichmann-lab/supervised-learning-dynamics/dnns/helper.py
pointer only (licence: NONE); the stored copy get_code serves, from wichmann-lab/robustness-development, is pointer only (licence: NONE) · get_code("c541c016fa27d34b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

find_csv_files Ran
ran; our contract draft was wrong, not the code
wichmann-lab/supervised-learning-dynamics/analysis/utils/helper.py
pointer only (licence: NONE) · get_code("030485e9a21606b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

load_model Not yet run
unverified (harvested, no recorded run)
wichmann-lab/supervised-learning-dynamics/dnns/helper.py
pointer only (licence: NONE) · get_code("ca2f0a7db8dc2aea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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.

plot_confusion_matrix_overall Not yet run
unverified (harvested, no recorded run)
wichmann-lab/supervised-learning-dynamics/analysis/utils/plotting.py
pointer only (licence: NONE) · get_code("a9236639e4745226")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wichmann-lab/supervised-learning-dynamics 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 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
dir_up 1 other paper
1 dated earlier
2205.10144 (2022-05)
The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks

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

Recent research has seen many behavioral comparisons between humans and deep neural networks (DNNs) in the domain of image classification. Often, comparison studies focus on the end-result of the learning process by measuring and comparing the similarities in the representations of object categories once they have been formed. However, the process of how these representations emerge-that is, the behavioral changes and intermediate stages observed during the acquisition-is less often directly and empirically compared. Here we report a detailed investigation of the learning dynamics in human observers and various classic and state-of-the-art DNNs. We develop a constrained supervised learning environment to align learning-relevant conditions such as starting point, input modality, available input data and the feedback provided. Across the whole learning process we evaluate and compare how well learned representations can be generalized to previously unseen test data. Comparisons across the entire learning process indicate that DNNs demonstrate a level of data efficiency comparable to human learners, challenging some prevailing assumptions in the field. However, our results also reveal representational differences: while DNNs' learning is characterized by a pronounced generalisation lag, humans appear to immediately acquire generalizable representations without a preliminary phase of learning training set-specific information that is only later transferred to novel data.

For agents

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

get_harvested_code_for_paper("2402.09303")
get_code_for_paper("2402.09303")
have("2402.09303")

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

curl https://syntology.ai/api/ran/2402.09303.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.09303.svg)](https://syntology.ai/paper/2402.09303)

Connect an agent — have() is free.