---
title: An image classifier is observed to designate a fluffy slipper as a c… — What is AI? Pattern-guessers, not people · tree and pragmatics
description: An image classifier is observed to designate a fluffy slipper as a cat. Ascertain the inference which may properly be drawn. Exam question 4 of lesson 1 «What is AI? Pattern-guessers, not people» of the AI course of Mova's primary school, with the dependency tree and pragmatics of the question and o
---

<!-- md -->
[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/questions/ai/1-what-is-ai/e4/)

<!-- crumbs -->
[home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [questions](https://md.mova.elamur.ai/free/en/corpora/questions/) / [AI](https://md.mova.elamur.ai/free/en/corpora/questions/ai/) / [What is AI? Pattern-guessers, not people](https://md.mova.elamur.ai/free/en/corpora/questions/ai/1-what-is-ai/) / e4

# Exam question 4 · What is AI? Pattern-guessers, not people

<!-- .ven lang=en -->
An image classifier is observed to designate a fluffy slipper as a cat. Ascertain the inference which may properly be drawn.

<!-- .vintro -->
**Mova's choice:** option 1 · **The right answer:** option 1 · right ✓ · **Who acts:** you · **What happens:** observe, designate, ascertain, draw · **To what, where:** image classifier, fluffy slipper, inference

<!-- .vabout -->
This is exam question 4 of lesson 1 «What is AI? Pattern-guessers, not people» of the AI course of Mova's primary school, asked in stiff, formal language. The page gives the question's syntax tree — a dependency tree in the style of Universal Dependencies — and its pragmatics clause by clause, then the 4 options as the student saw them, each with its tree and pragmatics. Every text is parsed by Mova itself. How the student answered it, with the score of every option and why: [the test at school](https://md.mova.elamur.ai/free/en/school-run/ai/1-what-is-ai/#e4).

## The question {#question}

<!-- .note -->
*Sentence 1:* An image classifier is observed to designate a fluffy slipper as a cat.

```conllu
# sent_id = question:ai:1-what-is-ai:e4:1
# text = An image classifier is observed to designate a fluffy slipper as a cat.
1	An	a	DET	DT	Definite=Ind|PronType=Art	3	det	_	_
2	image	image	NOUN	NN	Number=Sing	3	compound	_	_
3	classifier	classifier	NOUN	NN	Number=Sing	5	nsubj:pass	_	_
4	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	5	aux:pass	_	_
5	observed	observe	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
6	to	to	PART	TO	_	7	mark	_	_
7	designate	designate	VERB	VB	VerbForm=Inf	5	xcomp	_	_
8	a	a	DET	DT	Definite=Ind|PronType=Art	10	det	_	_
9	fluffy	fluffy	ADJ	JJ	Degree=Pos	10	amod	_	_
10	slipper	slipper	NOUN	NN	Number=Sing	7	obj	_	_
11	as	as	ADP	IN	_	13	case	_	_
12	a	a	DET	DT	Definite=Ind|PronType=Art	13	det	_	_
13	cat	cat	NOUN	NN	Number=Sing	7	obl	_	SpaceAfter=No
14	.	.	PUNCT	.	_	5	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **observe** | present · passive |  | a image classifier |  |  |  |  | tree rules |
| 2 | **designate** | to-infinitive |  | a fluffy slipper |  |  |  | as a cat | vn appoint-29.1 «NP V NP PP.attribute»: agent=Agent slipper=Theme as cat=Attribute |

<!-- .note -->
One row per clause the reader finds. «not said here»: a role filled from the clause above. «roles by»: a VerbNet class and frame when one fits the verb, else the reader's rules on the tree.

<!-- .note -->
*Sentence 2:* Ascertain the inference which may properly be drawn.

```conllu
# sent_id = question:ai:1-what-is-ai:e4:2
# text = Ascertain the inference which may properly be drawn.
1	Ascertain	ascertain	VERB	VB	Mood=Imp|VerbForm=Fin	0	root	_	_
2	the	the	DET	DT	Definite=Def|PronType=Art	3	det	_	_
3	inference	inference	NOUN	NN	Number=Sing	1	obj	_	_
4	which	which	PRON	WDT	PronType=Rel	8	nsubj:pass	_	_
5	may	may	AUX	MD	VerbForm=Fin	8	aux	_	_
6	properly	properly	ADV	RB	_	8	advmod	_	_
7	be	be	AUX	VB	VerbForm=Inf	8	aux:pass	_	_
8	drawn	draw	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	3	acl:relcl	_	SpaceAfter=No
9	.	.	PUNCT	.	_	1	punct	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **ascertain** | imperative | you *not said here* | the inference |  |  |  |  | vn discover-84 «NP V NP»: agent=Agent inference=Topic |
| 2 | **draw** | may · passive |  | the inference |  |  |  | properly *property* | vn scribble-25.2-1 «NP V NP»: subject=Theme |

## The options {#options}

### Option 1 · ← Mova's choice · ✓ the right answer {#o1}

<!-- .ven lang=en -->
The classifier has learned visual resemblance from examples and may be misled by similar objects

<!-- fold The tree, 15 words -->
```conllu
# sent_id = question:ai:1-what-is-ai:e4:o1:1
# text = The classifier has learned visual resemblance from examples and may be misled by similar objects
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	classifier	classifier	NOUN	NN	Number=Sing	4	nsubj	_	_
3	has	have	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	aux	_	_
4	learned	learn	VERB	VBN	Tense=Past|VerbForm=Part	0	root	_	_
5	visual	visual	ADJ	JJ	Degree=Pos	6	amod	_	_
6	resemblance	resemblance	NOUN	NN	Number=Sing	4	obj	_	_
7	from	from	ADP	IN	_	8	case	_	_
8	examples	example	NOUN	NNS	Number=Plur	4	obl	_	_
9	and	and	CCONJ	CC	_	12	cc	_	_
10	may	may	AUX	MD	VerbForm=Fin	12	aux	_	_
11	be	be	AUX	VB	VerbForm=Inf	12	aux:pass	_	_
12	misled	mislead	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	4	conj	_	_
13	by	by	ADP	IN	_	15	case	_	_
14	similar	similar	ADJ	JJ	Degree=Pos	15	amod	_	_
15	objects	object	NOUN	NNS	Number=Plur	12	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **learn** | present · perfect | the classifier | visual resemblance |  | examples |  |  | vn learn-14-2-1 «NP V NP PP.source»: agent=Agent resemblance=Topic from example=Source |
| 2 | **mislead** | may · passive | similar objects |  |  |  |  |  | vn trick-59.2 «NP V NP»: agent=Agent |

### Option 2 {#o2}

<!-- .ven lang=en -->
The classifier possesses knowledge that the slipper belongs to a cat

```conllu
# sent_id = question:ai:1-what-is-ai:e4:o2:1
# text = The classifier possesses knowledge that the slipper belongs to a cat
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	classifier	classifier	NOUN	NN	Number=Sing	3	nsubj	_	_
3	possesses	possess	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	_
4	knowledge	knowledge	NOUN	NN	Number=Sing	3	obj	_	_
5	that	that	SCONJ	IN	_	8	mark	_	_
6	the	the	DET	DT	Definite=Def|PronType=Art	7	det	_	_
7	slipper	slipper	NOUN	NN	Number=Sing	8	nsubj	_	_
8	belongs	belong	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	3	advcl	_	_
9	to	to	ADP	IN	_	11	case	_	_
10	a	a	DET	DT	Definite=Ind|PronType=Art	11	det	_	_
11	cat	cat	NOUN	NN	Number=Sing	8	obl	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **possess** | present | the classifier | knowledge |  |  |  |  | vn own-100.1 «NP V NP»: agent=Pivot knowledge=Theme |
| 2 | **belong** | present | the slipper |  |  |  |  | to a cat | vn attend-107.4-2 «NP V PP»: agent=Theme |

### Option 3 {#o3}

<!-- .ven lang=en -->
The classifier has been deliberately instructed to deceive its users

```conllu
# sent_id = question:ai:1-what-is-ai:e4:o3:1
# text = The classifier has been deliberately instructed to deceive its users
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	classifier	classifier	NOUN	NN	Number=Sing	6	nsubj:pass	_	_
3	has	have	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	6	aux	_	_
4	been	be	AUX	VBN	Tense=Past|VerbForm=Part	6	aux:pass	_	_
5	deliberately	deliberately	ADV	RB	_	6	advmod	_	_
6	instructed	instruct	VERB	VBN	Tense=Past|VerbForm=Part|Voice=Pass	0	root	_	_
7	to	to	PART	TO	_	8	mark	_	_
8	deceive	deceive	VERB	VB	VerbForm=Inf	6	xcomp	_	_
9	its	its	PRON	PRP$	Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs	10	nmod:poss	_	_
10	users	user	NOUN	NNS	Number=Plur	8	obj	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **instruct** *speech: other* | present · perfect · passive |  | the classifier |  |  |  | deliberately *property* | vn advise-37.9-1 «NP V NP how S\_INF»: subject=Recipient clause=Topic |
| 2 | **deceive** | to-infinitive |  | classifier's users |  |  |  |  | vn trick-59.2 «NP V NP»: agent=Agent user=Patient |

### Option 4 {#o4}

<!-- .ven lang=en -->
The classifier is functioning without error, slippers being a variety of cat

```conllu
# sent_id = question:ai:1-what-is-ai:e4:o4:1
# text = The classifier is functioning without error, slippers being a variety of cat
1	The	the	DET	DT	Definite=Def|PronType=Art	2	det	_	_
2	classifier	classifier	NOUN	NN	Number=Sing	4	nsubj	_	_
3	is	be	AUX	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	cop	_	_
4	functioning	functioning	ADJ	JJ	Degree=Pos	11	amod	_	_
5	without	without	ADP	IN	_	6	case	_	_
6	error	error	NOUN	NN	Number=Sing	4	obl	_	SpaceAfter=No
7	,	,	PUNCT	,	_	8	punct	_	_
8	slippers	slipper	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	4	conj	_	_
9	being	be	AUX	VBG	Tense=Pres|VerbForm=Part	11	cop	_	_
10	a	a	DET	DT	Definite=Ind|PronType=Art	11	det	_	_
11	variety	variety	NOUN	NN	Number=Sing	0	root	_	_
12	of	of	ADP	IN	_	13	case	_	_
13	cat	cat	NOUN	NN	Number=Sing	11	nmod	_	_
```

<!-- .fr -->
| # | verb | tense, mood | who | what, whom | to whom | where | when | other | roles by |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **is** | present | the classifier |  |  |  |  | without error; functioning *property* | tree rules |
| 2 | **slipper** | present | the classifier *not said here* |  |  |  |  |  | tree rules |
| 3 | **is a** | gerund |  | a functioning variety |  |  |  | of cat | tree rules |

<!-- div src -->

**Text:** the tests of Mova's primary school, written for Mova (`world/data/school/`), as the course runner gave them to the student. **Trees:** Mova's own parse — the `en` model on the CPU, when the site is built — not checked by a teacher; they may be wrong. **Frames:** Mova's frames reader (`prag`), each text read on its own. Elamur Cosmic License.

<!-- /div -->

<!-- pn -->
- ← previous: [What is AI? Pattern-guessers, not people, exam 3](https://md.mova.elamur.ai/free/en/corpora/questions/ai/1-what-is-ai/e3/)
- next →: [How a language model learns: guessing…, test 1](https://md.mova.elamur.ai/free/en/corpora/questions/ai/2-guessing-the-next-word/t1/)
- ↑ back to [What is AI? Pattern-guessers, not people](https://md.mova.elamur.ai/free/en/corpora/questions/ai/1-what-is-ai/)