Building Machines That Learn and Think Like People

Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman · Behavioral and Brain Sciences / arXiv · 2017 · cognitive-psychology · 10.1017/S0140525X16001837 · record lake2017-machines-learn-think
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. Claim type 'critique' captures the dominant shape (the case against current deep learning as a route to human-like intelligence); the article also has a constructive proposal component (the core ingredients) that the single-value facet cannot express. method 'review' matches the paper's own description of itself as reviewing cognitive science; it is a BBS target article / position paper rather than a new empirical study, and its only original data is an informal self-experiment ('In informal experiments with two of the authors playing Frostbite on a Javascript emulator'). The two 'contradicts' relations are hedged in the original ('may be learning ... in a very different way'), and what is contradicted is the interpretation of those systems as human-like, not their reported performance - the four allowed relation types have no 'critiques' option. Replication status 'untested' since the article makes no replicable empirical claim of its own. 2026-08-14, 2026-08-17 and 2026-08-25 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

This record’s own method is review, and the tags below follow from that. A review’s findings, quantities and statistics are things stated IN this paper, and some of them report results obtained elsewhere. No tag on this page names a different author. Measured across every review in this corpus, 81% of a review’s tags carry no citation at all — most of them are the review speaking. The corpus does not adjudicate the rest: read an unmarked tag as a claim this paper makes, not necessarily one it made first.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
deep learning 11 fields · artificial intelligence 4 fields · neural networks 3 fields · statistical-significance 2 fields · convolutional neural network 2 fields · people 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 13 concept tags on this paper, 9 are grounded in a quoted sentence. 3 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

intuitive physics compositionality learning-to-learn causal model MNIST richer representations human-level performance ImageNet neural networks people deep learning PDP models Intuitive psychology PERFORMANCE PARITY IS GRANTED AND SIMILARITY DENIED IN CONSECUTIVE SENTENCES: these systems achieve performance that EQUALS OR EVEN BEATS HUMANS IN SOME RESPECTS - DESPITE their biological inspiration and performance achievements, they DIFFER FROM HUMAN INTELLIGENCE IN CRUCIAL WAYS. Matching a score is separated from being alike, and the concession comes first THE CRITERION IS SPLIT INTO TWO DIMENSIONS SO THAT A SYSTEM CAN FAIL ON EITHER: truly HUMAN-LIKE learning and thinking machines will have to reach beyond current engineering trends in BOTH WHAT THEY LEARN, AND HOW THEY LEARN IT. One adjective, two independent requirements A QUESTION IS DECLARED OLDER THAN THE NAMES OF BOTH FIELDS THAT ASK IT: the questions of whether and how AI should relate to human cognitive psychology are OLDER THAN THE TERMS ARTIFICIAL INTELLIGENCE AND COGNITIVE PSYCHOLOGY. The problem existed before either vocabulary did, which means neither vocabulary was built to state it THE POSITION BEING ARGUED AGAINST IS QUOTED FROM A TEXTBOOK, AS AN ANALOGY ABOUT ABANDONING IMITATION: the quest for ARTIFICIAL FLIGHT succeeded WHEN THE WRIGHT BROTHERS AND OTHERS STOPPED IMITATING BIRDS and started using wind tunnels and learning about aerodynamics. The rival view is presented in its own strongest form, in its own words, with a page reference A DEFENDER'S HOPE IS GRANTED SYMPATHY AND THEN DOUBTED, WITH THE DOUBT MARKED AS UNCERTAIN: Quotation withheld Disagreement stated as an uncertainty about the opponent's prospects rather than as a refutation THE BENCHMARK'S SCALE IS MADE CONCRETE BY NAMING THE OBJECTS: benchmark tasks provide HUNDREDS OR THOUSANDS OF EXAMPLES PER CLASS - 1000 HAIRBRUSHES, 1000 PINEAPPLES, etc. - and one dataset includes 6000 examples of each handwritten digit. An abstract quantity is turned into a picture of what the quantity is made of TWO QUANTITIES A SINGLE COMPARISON CONFLATES ARE SEPARATED IN A FOOTNOTE: the time required to train the network - **COMPUTE TIME** - IS NOT THE SAME AS THE GAME (EXPERIENCE) TIME, and compute time CAN BE LONGER. Two clocks under one word, distinguished where a reader might not look A METRIC IS DESCRIBED AS DESIGNED TO BLOCK ONE SPECIFIC CHEAT, AND ITS RIVALS' STATUS IS DECLARED UNKNOWN: the reported scores use the HUMAN STARTS measure, DESIGNED TO PREVENT NETWORKS FROM JUST MEMORIZING LONG SEQUENCES OF SUCCESSFUL ACTIONS FROM A SINGLE STARTING POINT - and faster learning and higher scores HAVE BEEN REPORTED USING OTHER METRICS, BUT IT IS UNCLEAR HOW WELL THE NETWORKS ARE GENERALIZING WITH THESE ALTERNATIVE METRICS. The number depends on which measure, and only one of them is known to mean what it says AN OPPOSING SCHOOL'S POSITION IS SUMMARISED AS A CLAIM ABOUT METAPHOR: proponents maintain that classic types of structured knowledge - graphs, grammars, rules, objects, programs - CAN BE USEFUL YET MISLEADING METAPHORS for characterizing thought, and that these structures are MORE EPIPHENOMENAL THAN REAL. The disagreement is over whether the vocabulary names things or describes them THE OBJECTION TO THE PAPER'S OWN COMPARISON IS RAISED BY THE PAPER, EARLY, AND FLAGGED AS ANTICIPATED: one might object that both challenges draw an UNFAIR COMPARISON between the speed of human learning and neural network learning - discussed in detail later, BUT WE FEEL IT IS IMPORTANT TO ANTICIPATE HERE AS WELL. The strongest attack on the paper's method is placed before the method is used AND THE REFRAMING THE PAPER ADOPTS IS QUOTED FROM AN ANONYMOUS REVIEWER OF AN EARLIER DRAFT: THEY MAY BE BETTER SEEN AS SOLVING DIFFERENT TASKS - the human ENCOUNTERING ONE IN A YEARS-LONG STRING OF PROBLEMS WITH RICH OVERLAPPING STRUCTURE, the network STARTING COMPLETELY FROM SCRATCH. The comparison fails not through a confound but because one phrase, `the task`, was covering two different things - and the authors reply WE AGREE A CAPACITY IS SHOWN TO PERSIST DESPITE THE PRACTICE THAT WOULD EXPLAIN IT: children are FAR MORE PRACTICED than adults at learning new concepts - ROUGHLY NINE OR TEN NEW WORDS EACH DAY - YET the ability for rapid ONE-SHOT learning DOES NOT DISAPPEAR IN ADULTHOOD. The obvious explanation for the skill is present in one group and the skill in both THE PAPER'S OWN CRITERIA ARE CALLED INGREDIENTS AND PLACED AFTER A REVIEW OF OTHER PEOPLE'S: first the criteria PREVIOUSLY OFFERED by cognitive scientists, developmental psychologists and AI researchers are reviewed - THEN what the authors VIEW AS THE ESSENTIAL INGREDIENTS is articulated. The list is presented as a synthesis with a named provenance, not as a definition artificial intelligence human intelligence causal models intuitive theories cognitive science pattern recognition deep reinforcement learning convolutional neural network Bayesian mean average of regression regression model statistical-significance review

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.1017/S0140525X16001837. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 4 · claim_type 1 · concept_edges 2 · concepts 9 · content_tags 18 · limitations 7 · mechanisms 13 · method 1 · phenomenon 1 · senses 4 · transfers 2

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; 1 of 2 relations here carries that mark. The rest are the tagger’s reading of the sentence quoted beside them.

This record holds no controls. A layer is empty when the tagger recorded nothing in it — which is not the same as the paper having nothing to record.

facet	tag	field	conf.	whose words
claim_type	critique Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	human-like learning and thinking in machines Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	review Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: review	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: PERFORMANCE PARITY IS GRANTED AND SIMILARITY DENIED IN CONSECUTIVE SENTENCES: these systems achieve performance that EQUALS OR EVEN BEATS HUMANS IN SOME RESPECTS - DESPITE their biological inspiration and performance achievements, they DIFFER FROM HUMAN INTELLIGENCE IN CRUCIAL WAYS. Matching a score is separated from being alike, and the concession comes first	`mechanisms[0]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: THE CRITERION IS SPLIT INTO TWO DIMENSIONS SO THAT A SYSTEM CAN FAIL ON EITHER: truly HUMAN-LIKE learning and thinking machines will have to reach beyond current engineering trends in BOTH WHAT THEY LEARN, AND HOW THEY LEARN IT. One adjective, two independent requirements	`mechanisms[1]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: A QUESTION IS DECLARED OLDER THAN THE NAMES OF BOTH FIELDS THAT ASK IT: the questions of whether and how AI should relate to human cognitive psychology are OLDER THAN THE TERMS ARTIFICIAL INTELLIGENCE AND COGNITIVE PSYCHOLOGY. The problem existed before either vocabulary did, which means neither vocabulary was built to state it	`mechanisms[2]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: THE POSITION BEING ARGUED AGAINST IS QUOTED FROM A TEXTBOOK, AS AN ANALOGY ABOUT ABANDONING IMITATION: the quest for ARTIFICIAL FLIGHT succeeded WHEN THE WRIGHT BROTHERS AND OTHERS STOPPED IMITATING BIRDS and started using wind tunnels and learning about aerodynamics. The rival view is presented in its own strongest form, in its own words, with a page reference	`mechanisms[3]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: A DEFENDER'S HOPE IS GRANTED SYMPATHY AND THEN DOUBTED, WITH THE DOUBT MARKED AS UNCERTAIN: Quotation withheld Disagreement stated as an uncertainty about the opponent's prospects rather than as a refutation	`mechanisms[4]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: THE BENCHMARK'S SCALE IS MADE CONCRETE BY NAMING THE OBJECTS: benchmark tasks provide HUNDREDS OR THOUSANDS OF EXAMPLES PER CLASS - 1000 HAIRBRUSHES, 1000 PINEAPPLES, etc. - and one dataset includes 6000 examples of each handwritten digit. An abstract quantity is turned into a picture of what the quantity is made of	`mechanisms[5]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: TWO QUANTITIES A SINGLE COMPARISON CONFLATES ARE SEPARATED IN A FOOTNOTE: the time required to train the network - COMPUTE TIME - IS NOT THE SAME AS THE GAME (EXPERIENCE) TIME, and compute time CAN BE LONGER. Two clocks under one word, distinguished where a reader might not look	`mechanisms[6]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: A METRIC IS DESCRIBED AS DESIGNED TO BLOCK ONE SPECIFIC CHEAT, AND ITS RIVALS' STATUS IS DECLARED UNKNOWN: the reported scores use the HUMAN STARTS measure, DESIGNED TO PREVENT NETWORKS FROM JUST MEMORIZING LONG SEQUENCES OF SUCCESSFUL ACTIONS FROM A SINGLE STARTING POINT - and faster learning and higher scores HAVE BEEN REPORTED USING OTHER METRICS, BUT IT IS UNCLEAR HOW WELL THE NETWORKS ARE GENERALIZING WITH THESE ALTERNATIVE METRICS. The number depends on which measure, and only one of them is known to mean what it says	`mechanisms[7]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: AN OPPOSING SCHOOL'S POSITION IS SUMMARISED AS A CLAIM ABOUT METAPHOR: proponents maintain that classic types of structured knowledge - graphs, grammars, rules, objects, programs - CAN BE USEFUL YET MISLEADING METAPHORS for characterizing thought, and that these structures are MORE EPIPHENOMENAL THAN REAL. The disagreement is over whether the vocabulary names things or describes them	`mechanisms[8]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: THE OBJECTION TO THE PAPER'S OWN COMPARISON IS RAISED BY THE PAPER, EARLY, AND FLAGGED AS ANTICIPATED: one might object that both challenges draw an UNFAIR COMPARISON between the speed of human learning and neural network learning - discussed in detail later, BUT WE FEEL IT IS IMPORTANT TO ANTICIPATE HERE AS WELL. The strongest attack on the paper's method is placed before the method is used	`mechanisms[9]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: EXTENDED so the span carries the authors' assent in full - "We agree, and indeed this is another way of putting our point here" - rather than stopping at "We agree". The two words alone would have left it unclear whether they were conceding the objection or adopting the reframing. They adopt it: an anonymous reviewer's sentence becomes the paper's own statement of its point. NOTE ALSO that the reviewer quotation has a PAGE NUMBER spliced inside it a few words earlier - "solving the same task 14 differently" - which is why the span starts at the following sentence. also in: AND THE REFRAMING THE PAPER ADOPTS IS QUOTED FROM AN ANONYMOUS REVIEWER OF AN EARLIER DRAFT: THEY MAY BE BETTER SEEN AS SOLVING DIFFERENT TASKS - the human ENCOUNTERING ONE IN A YEARS-LONG STRING OF PROBLEMS WITH RICH OVERLAPPING STRUCTURE, the network STARTING COMPLETELY FROM SCRATCH. The comparison fails not through a confound but because one phrase, `the task`, was covering two different things - and the authors reply WE AGREE	`mechanisms[10]`	0.85	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: A CAPACITY IS SHOWN TO PERSIST DESPITE THE PRACTICE THAT WOULD EXPLAIN IT: children are FAR MORE PRACTICED than adults at learning new concepts - ROUGHLY NINE OR TEN NEW WORDS EACH DAY - YET the ability for rapid ONE-SHOT learning DOES NOT DISAPPEAR IN ADULTHOOD. The obvious explanation for the skill is present in one group and the skill in both	`mechanisms[11]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: THE PAPER'S OWN CRITERIA ARE CALLED INGREDIENTS AND PLACED AFTER A REVIEW OF OTHER PEOPLE'S: first the criteria PREVIOUSLY OFFERED by cognitive scientists, developmental psychologists and AI researchers are reviewed - THEN what the authors VIEW AS THE ESSENTIAL INGREDIENTS is articulated. The list is presented as a synthesis with a named provenance, not as a definition	`mechanisms[12]`	0.95	the tagger's words
limitations	planning in complex (model-based) systems is cumbersome and slow for real-time control Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the real-time control claim: PLANNING IN COMPLEX MODELS IS CUMBERSOME AND SLOW	`limitations[0]`		the tagger's words
limitations	The article says very little about natural language, a capacity the authors concede is central to human intelligence. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the scope of the whole article: WE HAVE SAID LITTLE ... ABOUT PEOPLE'S ABILITY TO COMMUNICATE AND THINK IN NATURAL LANGUAGE, A DISTINCTIVELY HUMAN COGNITIVE CAPACITY WHERE MACHINE CAPABILITIES LAG STRIKINGLY	`limitations[1]`		the tagger's words
limitations	The proposed list of core ingredients is explicitly not claimed to be complete. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the list of core ingredients: WE DID NOT INTEND OUR LIST TO BE COMPLETE	`limitations[2]`		the tagger's words
limitations	The authors concede the objection that humans bring far richer prior experience to a new task than a network does, which complicates the learning-speed comparisons the paper rests on. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the human-machine comparison: humans bring far richer prior experience to a new task than a network does, which the authors concede as an objection	`limitations[3]`		the tagger's words
limitations	Their own prior model of the Characters Challenge does not capture the full human ability. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[4]`		the tagger's words
limitations	Equal performance on the benchmark is stated not to indicate equal capability. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any comparison of human and network ability based on these benchmarks: the authors state that performing equally well on MNIST and other large-scale image classification tasks does not mean humans and networks learn and think in the same way	`limitations[5]`	1.0	the tagger's words
limitations	The human-level comparison is stated for specific data sets, with one described as within reach rather than reached. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any claim that networks have matched human performance: the authors report an error rate very close to human-level on one task and describe human-level performance as within reach on the ImageNet benchmark	`limitations[6]`	1.0	the tagger's words
transfers	the simulation engine that renders a game world is used as the model of intuitive physics: the mind is proposed to run something like it to predict what happens next in a scene Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`	0.95	the tagger's words
transfers	the representations and algorithms of the connectionist approach were drawn from neuroscience rather than from cognitive psychology, and the paper marks that as the choice which shaped it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[1]`	0.95	the tagger's words
concepts	MNIST Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: MNIST	`concepts[4]`		the paper's words
concepts	richer representations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: richer representations	`concepts[5]`		the paper's words
concepts	human-level performance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: human-level performance	`concepts[6]`		the paper's words
concepts	ImageNet Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ImageNet	`concepts[7]`		the paper's words
concepts	neural networks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: neural networks	`concepts[8]`		the paper's words
concepts	people Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: people	`concepts[9]`		the paper's words
concepts	deep learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: deep learning	`concepts[10]`	0.95	the paper's words
concepts	PDP models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: PDP models	`concepts[11]`	0.95	the paper's words
concepts	Intuitive psychology Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Intuitive psychology	`concepts[12]`	0.9	the paper's words
senses	equal benchmark performance - NOT EQUAL CAPABILITY: the authors state that humans and networks may score the same on MNIST and other large-scale image classification tasks while not learning or thinking in the same way, and name two respects in which they differ - the number of examples needed and the richness of what is learned Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	human-level performance - A PHRASE ATTACHED TO PARTICULAR DATA SETS: reported as an error rate very close to human on one task and as within reach on another, so the expression names a relation to a specific benchmark rather than a general parity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	the list of differences - A FLOOR, NOT A SET: the authors write that there are AT LEAST two important differences before naming two, so the enumeration is explicitly open and a reader who treats the two as the complete account has closed a list the authors left open Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
senses	`deep learning` / `PDP models` - A RENAMING ACROSS THIRTY YEARS, AND THE PAPER SAYS THE CONTENT DID NOT CHANGE WITH THE NAME. `The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models.` Both names describe the same objects and neither is wrong; what changed is which property the field chose to put in the name - PDP named the computation (parallel, distributed), `deep` names the layer count. The paper then glosses the new name explicitly: `“Deep” refers to the fact that more powerful models can be built by composing many layers of representation.` Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	0.95	the tagger's words
claim_relations	contradicts → the view that current deep-learning systems capture human intelligence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	builds-on → Lake, Salakhutdinov, & Tenenbaum (2015) probabilistic program induction for handwritten characters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	contradicts → V. Mnih et al. (2015) Deep Q-Network playing Atari games Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	contradicts → AlphaGo (Silver et al., 2016) as a system that understands the game Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
concept_edges	neural networks —contrasted-with→ people Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: how many examples are needed and how rich the learned representation is - a list the authors mark as at least two · strength of the relation: 1 also in: neural networks · people	`concept_edges[0]`		the tagger's words
concept_edges	deep learning —renamed-across-fields→ PDP models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.9 · note: Both names sit inside the one span, as the type requires. Weight 0.9 rather than 1.0: the paper says 'often even the same learning algorithms' - the identity is asserted for the commitments and hedged for the algorithms. The split is across TIME rather than across a field boundary, which is the nearest type available and is recorded here as such. · the relation stated: neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says deep learning shares the representational commitments of the earlier PDP models; renamed-across-fields is loose. also in: deep learning · PDP models	`concept_edges[1]`	0.9	the tagger's words
content_tags	3 — proposed ingredients (a,b,c) for human-like machines Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	~half — Krizhevsky convnet cut the prior error rate Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	late 1980s — when HMMs became the leading speech approach Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[2]`		the tagger's words
content_tags	these systems differ in crucial ways from how humans think Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`		the tagger's words
content_tags	human-like machines should build causal models of the world Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	learning should be grounded in intuitive physics and psychology Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`		the tagger's words
content_tags	machines should harness compositionality and learning-to-learn Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[3]`		the tagger's words
content_tags	causal models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: causal models	`content_tags.variables[1]`		the tagger's words
content_tags	intuitive theories Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: intuitive theories	`content_tags.variables[2]`		the tagger's words
content_tags	compositionality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: compositionality	`content_tags.variables[3]`		the tagger's words
content_tags	deep learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: deep learning	`content_tags.definitions[0]`		the tagger's words
content_tags	deep reinforcement learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: deep reinforcement learning	`content_tags.definitions[1]`		the tagger's words
content_tags	convolutional neural network Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: convolutional neural network	`content_tags.definitions[2]`		the tagger's words
content_tags	learning-to-learn Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learning-to-learn	`content_tags.definitions[3]`		the tagger's words
content_tags	Bayesian Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Bayesian	`content_tags.statistics[0]`		the tagger's words
content_tags	mean Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: mean	`content_tags.statistics[1]`		the tagger's words
content_tags	EVIDENCE CORRECTED (RE-GROUNDED) · regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. EVIDENCE CORRECTED: RE-GROUNDED. The old evidence was 'Quotation withheld' - THE TITLE OF A PAPER BY SOMEBODY ELSE, sitting in this paper's bibliography. An internal tool cuts the reference list on purpose, for exactly this reason, so the row was invisible to every grounding check. lake2017 uses 'regression' once in its own prose and that sentence is now the evidence. also in: regression	`content_tags.statistics[2]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical-significance	`content_tags.statistics[3]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.