Papers › Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

30 May 2016NeurIPS 2016 12arXiv:1605.09304archive 2025-07-28

Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune

Deep neural networks (DNNs) have demonstrated state-of-the-art results on many pattern recognition tasks, especially vision classification problems. Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs. One path to understanding how a neural network functions internally is to study what each of its neurons has learned to detect. One such method is called activation maximization (AM), which synthesizes an input (e.g. an image) that highly activates a neuron. Here we dramatically improve the qualitative state of the art of activation maximization by harnessing a powerful, learned prior: a deep generator network (DGN). The algorithm (1) generates qualitatively state-of-the-art synthetic images that look almost real, (2) reveals the features learned by each neuron in an interpretable way, (3) generalizes well to new datasets and somewhat well to different network architectures without requiring the prior to be relearned, and (4) can be considered as a high-quality generative method (in this case, by generating novel, creative, interesting, recognizable images).

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 3 repositories, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

AndyDodss/iicnn mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generating Images with Perceptual Similarity Metrics based on Deep Networks (arXiv:1602.02644; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
Evolving-AI-Lab/synthesizing mentioned on GitHubcaffe2MITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
KamitaniLab/cnnpref mentioned on GitHubcaffe2Syntology: 2 samples, 0 ran · 2 unverified report
KamitaniLab/icnn mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generating Images with Perceptual Similarity Metrics based on Deep Networks (arXiv:1602.02644; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
ndey96/deep-generator-network pytorchMITSyntology: 6 samples, 4 ran (1 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
5ran
5unverified

Licence: 3 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Evolving-AI-Lab/synthesizing community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
patchShow.py ran MIT (permissive) · 74a74b343c22fd81 · report fixture: signature img:ndarray/3/float, out_range:tuple/1/float, in_range:NoneType/0/? · returned ndarray · level recorded 2026-09-26
patchShow_single patchShow.py ran MIT (permissive) · c9dfeeed15b41474 · report fixture: signature images:ndarray/4/float, out_range:tuple/1/float, in_range:NoneType/0/? · returned ndarray · level recorded 2026-09-26
patchShow patchShow.py unverified MIT (permissive) · c4c6fdc763e9b844 · report
KamitaniLab/cnnpref community (archive-listed) 2 samples, 0 ran · 2 unverified
generate_image in 15 papers cnnpref/prefer_img_gd.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · b43d90577686455e · report
generate_image in 15 papers cnnpref/prefer_img_dgn_gd.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · f4b8e2487402d23c · report
ndey96/deep-generator-network community (archive-listed) 6 samples, 4 ran (1 instrument-failed) · 2 unverified
compute_loss in 97 papers
census: 11 implementations from 11 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
loss_stub.py ran MIT (permissive) · b0e6e987c2ef0cfb · report fixture: signature y:Tensor/4/float, x:Tensor/4/float, gx:Tensor/4/float, egx:Tensor/4/float, cgx:Tensor/2/float, cy:Tensor/2/float, dgx:Tensor/4/float, dy:Tensor/4/float, t_ones:Tensor/1/float, t_zeros:Tensor/1/float, bce:callable/0/?, mse:callable/0/?, lambda_feat:float/0/float, lambda_adv:float/0/float, lambda_img:float/0/float · returned tuple · level recorded 2026-09-26
convert in 76 papers synthesize.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 4c4cd96456054cfe · report fixture: returned ndarray · level recorded, date not recorded
get_optimizers in 7 papers optimizer_stub.py ran MIT (permissive) · 5f72f9c63bb450a3 · report fixture: signature DS:callable/0/?, lr:float/0/float · returned tuple · level recorded 2026-09-26
process_img in 6 papers gen_init_compare.py ran fingerprinted MIT (permissive) · d73ff14130ee6a57 · report fixture: signature img:Tensor/4/float · returned ndarray · level recorded 2026-09-26
get_data_tools data_stub.py unverified MIT (permissive) · 3c30dcac42056712 · report
load_checkpoint in 277 papers checkpoint_stub.py unverified MIT (permissive) · a50752815479c30b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections