Questions tagged [knowledge-representation]

For questions about methods/intuitions/proofs/improvements in the knowledge representation in a problem to be solved by Artificially Intelligent agent.

Filter by
Sorted by
Tagged with
1 vote
2 answers
198 views

How do language models know what they don't know - and report it?

Again and again I ask myself what goes on in a pre-trained transformer-based language model (like ChatGPT9) when it comes to "know" that it cannot give an appropriate answer and either ...
Hans-Peter Stricker's user avatar
0 votes
0 answers
120 views

Can an LLM such as GPT learn from a sentence prediction that is close in meaning but drastically different in wording?

Consider this example: husband cheats on wife, AI predicts that wife gets angry. AI predicts that wife may either scream or throw things, with screaming a higher probability. Turns out in reality ...
Yan King Yin's user avatar
0 votes
0 answers
48 views

How to relate the definition for entailment, with soundness and completeness?

Is it fair enough to say for a language model, φ, which makes certain variable A true, and if φ also makes another variable B true, then we can conclude: A ⊨ B And for a certain inference calculus c,...
Carpediem's user avatar
1 vote
1 answer
69 views

Are my attempts to write "There exists a student studying all the subjects of the information technology subject" in FOL correct? [closed]

I have the following sentence, which I need to write in FOL There exists a student studying all the subjects of the information technology subject I don't know how $\forall$ can be combined with the ...
chews's user avatar
  • 13
0 votes
0 answers
23 views

ANN Input vector representing a network of contests's outcomes between thousands of individuals?

Let's say I have 1000 participants within a tournament, each of the participants having a single ID. One instance of this tournament is a 1 vs 1 contest when one wins and the other loses. Now let's ...
Stak33's user avatar
  • 1
1 vote
0 answers
46 views

How to develop an Entity linking system able to detect custom entities?

I am trying to build an entity linking system that links entities found in a text to entities on Wikipedia. If no Wikipedia page seems to match this entity, the systems will assume to have found a new ...
Giovanni Del Gallo's user avatar
1 vote
0 answers
15 views

What are other types of knowledge bases except entity-entric KB?

I learned a term entity-centric knowledge base, then I wonder what the non entity-centric knowledge graphs are? I googled by keys words "entity-centric knowledge base vs" and got some ...
Lerner Zhang's user avatar
1 vote
2 answers
99 views

Knowledge graph progress from 2012 to 2022?

I watched this lecture by professor Xin Wang, and a picture in the beginning interested me: The confusing thing is that this lecture was delivered on Sep. 19, 2022, but it seems from the diagram ...
Lerner Zhang's user avatar
1 vote
1 answer
50 views

Reasoning about 2d spatial square configuration

I am trying to use RCC8 algebra relations and axioms in order to tackle the following problem : We consider the below configuration and square $x$ such that "$x$ NTPP $a$" and "$x$ TPP $...
nick's user avatar
  • 113
2 votes
0 answers
73 views

Knowledge representation and reasoning(KRR) over a Image scene: Neurosymbolic AI

What are the ways and SOTA in domain of knowledge representation and reasoning over scene. Suppose there are 3 objects in the scene and which objects needs to be picked first among them is governed by ...
bigboss's user avatar
  • 31
0 votes
1 answer
249 views

How do I show the relationship between theories and models using Conceptual Graphs?

The Mereology Theory below contains three first-order axioms that represent a part of a mereology theory. For this posting, it is important that the set of axioms should be considered as a theory. ...
Patrick Browne's user avatar
1 vote
0 answers
14 views

Is there some way for us to know if the neural network internally finds an association between labels?

I have a question about the association between labels. Say my neural network performs multi-labeling in its output layer. Now, if one of the labels is for whether a person lives in city $X$, another ...
Abhiram Natarajan's user avatar
2 votes
0 answers
377 views

How are theories represented using Conceptual Graphs?

Theory 1 shows three axioms and two definitions, written in First Order Logic (FOL), that represents a fragment of a mereology theory. For this posting, it is important that the set of axioms is ...
Patrick Browne's user avatar
1 vote
0 answers
63 views

Apart from ontologies, which other methods for knowledge representation are there in Artificial Intelligence?

From what I have been reading, I see statements like Ontology is a common method used for knowledge representation in artificial intelligence. But there is never really a discussion around what ...
ofithch79's user avatar
  • 139
0 votes
1 answer
55 views

What algorithm to use to classify data by spatial relations?

Let's assume I have dataset of image-like 2D samples where values can be divided into few discrete levels (for example 1, 2, 3 and 4) like in the image below, where each color maps different value, ...
GKozinski's user avatar
  • 1,240
2 votes
0 answers
64 views

How to add prior information when predicting using deep learning models?

Background I'm building a binary classification model for a pair match problem using CNN, e.g. whether person A1 likes product B1 or not. Model input features are sequence features (text descriptions) ...
user3915365's user avatar
5 votes
3 answers
3k views

What are the differences between a knowledge base and a knowledge graph?

During my readings, I have seen many authors using the two terms interchangeably, i.e. as if they refer to the same thing. However, we all know about Google's first quotation of "knowledge graph&...
Betty's user avatar
  • 151
1 vote
1 answer
322 views

How can I draw a conceptual dependency for the statement "Place all ingredients in a bowl and mix thoroughly"?

I stumbled across a question asking to draw a conceptual dependency for the following statement: Place all ingredients in a bowl and mix thoroughly My attempt so far Explanation: Both the sender ...
Pranav Dinesh's user avatar
4 votes
3 answers
198 views

What would be a good internal language for an AI?

For an AI to represent the world, it would be good if it could translate human sentences into something more precise. We know, for example, that mathematics can be built up from set theory. So ...
zooby's user avatar
  • 2,186
1 vote
0 answers
41 views

How would we define a set that contains itself within a knowledge ontology?

How would we define a set that contains itself within a knowledge ontology? I am thinking that set membership would probably inherit from a generic base class of total containment from which both ...
polcott's user avatar
  • 111
3 votes
0 answers
66 views

Is the Assumption-based Truth Maintenance System still used?

Is the Assumption-based Truth Maintenance System still used to maintain consistency while explicitly accounting for assumptions?
Helios's user avatar
  • 31
2 votes
3 answers
220 views

Who is working on explaining the knowledge encoded into machine learning models? [duplicate]

The thing about machine learning (ML) that worries me is that "knowledge" acquired in ML is hidden: we usually can't explain the criteria or methods used by the machine to provide an answer ...
S. McGrew's user avatar
  • 363
2 votes
1 answer
1k views

What is the difference between a semantic network and an ontology?

What is the difference between a semantic network and an ontology? How are they related? I have not found any article that describes how these two concepts are related.
Pritul Dave's user avatar
0 votes
1 answer
44 views

How would an AI understand grids?

OK, now I think an AI must view grids in a different way to computers. For example a computer would represent a grid like this: ...
zooby's user avatar
  • 2,186
3 votes
1 answer
207 views

Is unsupervised disentanglement really impossible?

In Locatello et al's Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations he claims to prove unsupervised disentanglement is impossible. His entire claim is ...
mshlis's user avatar
  • 2,349
12 votes
5 answers
6k views

Why do we need common sense in AI?

Let's consider this example: It's John's birthday, let's buy him a kite. We humans most likely would say the kite is a birthday gift, if asked why it's being bought; and we refer to this reasoning ...
Titan's user avatar
  • 133
1 vote
0 answers
27 views

Is there any readily available concept/topic tree?

I am looking for dataset in tree structure that captures the hierarchy of concepts. For example, something like, ...
Vivek Krishna's user avatar
1 vote
0 answers
217 views

What is the difference between Knowledge Representation and Automated Reasoning?

Knowledge Representation and Automated Reasoning are two AI subfields which seem to have something to do with reasoning. However, I can't find any information online about their relationship. Are ...
olinarr's user avatar
  • 745
2 votes
1 answer
251 views

Are Relational DBs and SQL used in Expert Systems?

In the book Prolog Programming for Artificial Intelligence, a large and intricate chapter (chapter 14) is dedicated to Expert Systems. In these systems, a knowledge-database is represented through ...
olinarr's user avatar
  • 745
2 votes
0 answers
136 views

Formulation of a sentence using FOL

I want to formulate the following sentence using FOL; I want also to know whether there any contradictions in it, or if it is consistent. Assuming human relations are binary: All Human Relations ...
ammu's user avatar
  • 133
1 vote
1 answer
64 views

Learning similarities between customers and offers representation

I am interested in a framework for learning the similarity of different input representations based on some common context. I have looked into word2vec, SVD and siamese networks, all of which are ...
user10283726's user avatar
5 votes
2 answers
926 views

When is a knowledge base consistent?

I am studying a knowledge base (KB) from the book "Artificial Intelligence: A Modern Approach" (by Stuart Russell and Peter Norvig) and from this series of slides. A formula is satisfiable ...
theantomc's user avatar
  • 263
8 votes
0 answers
111 views

What are the current trends/open questions in logics for knowledge representation?

What are the future prospects in near future from a theoretical investigation of description logics, and modal logics in the context of artificial intelligence research?
mfioah's user avatar
  • 81
7 votes
1 answer
2k views

Did Turing foresee the required capabilities to pass the Turing test?

In Section 1.1 of Artificial Intelligence: A Modern Approach, it is stated that a computer which passes the Turing Test would need 4 capabilities, and that these 4 capabilities comprise most of the ...
alwaysLearningABC's user avatar
2 votes
2 answers
88 views

How to mathematically/logically represent the sense of sentences like "The cat drinks milk"?

I am absolutely new in the AI area. I would like to know how to mathematically/logically represent the sense of sentences like: The cat drinks milk. Sun is yellow. I was at work yesterday. So, that ...
DmitryBoyko's user avatar
1 vote
2 answers
3k views

Training an AI to play Starcraft 2 with superhuman level of performance?

I'm interested in working on challenging AI problems, and after reading this article (https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/) by DeepMind and ...
Pablo Messina's user avatar
4 votes
2 answers
214 views

As a starter: what is the form of training data for image processing

What we are doing in the image processing training. We are storing some form of data which is going to act as the knowledge or experience of the system. In which form can the system store it's ...
Sathish Kumar D's user avatar
3 votes
0 answers
92 views

Answer Set Programming - Make a Fact INVALID

I have a question regarding Answer Set Programming on how to make an existing fact invalid, when there is already (also) a default statement present in the Knowledge Base. For example, there are two ...
theRam's user avatar
  • 31
8 votes
1 answer
3k views

What is the difference between logic-based and rule-based AI?

I always thought rule-based was synonymous with logic-based AI. Logic has axioms and rules of inference, whereas rule-based AI has a knowledge base (essentially, axioms) and if-then rules to create ...
samlaf's user avatar
  • 211
8 votes
3 answers
414 views

What is meant by "known" in "A knowledge-base exhibits complete knowledge if and only if, for every $P$, $P$ or $\neg P$ is known"?

I have a question as to what it means for a knowledge-base to be consistent and complete. I've been looking into non-monotonic logic and different formalisms for it from the book "Knowledge ...
Parry's user avatar
  • 181
16 votes
3 answers
2k views

What roles knowledge bases play now and will play in the future?

Nowadays, artificial intelligence seems almost equal to machine learning, especially deep learning. Some have said that deep learning will replace human experts, traditionally very important for ...
Lerner Zhang's user avatar
2 votes
0 answers
903 views

How do I translate these English sentences into first-order logic without quantifiers?

I have to translate the following English sentences into First-Order Logic without using quantifiers: Everyone on flight 815 has a story. No one knows what is inside the hatch. Someone on the island ...
New_Coder's user avatar
  • 121
5 votes
2 answers
363 views

What does Brooks mean by "representation"?

For a class, I'm reading Brooks' "Intelligence without representation". The introduction is dedicated to slating representation as a focus for AI development. I've read that representation ...
Jansky's user avatar
  • 153
4 votes
3 answers
187 views

Given statements $A$ and $B$, are the formulae $(\lnot A) \land (\lnot B)$ and $(\lnot A) \lor (\lnot B)$ equivalent?

If I have 2 statements, say $A$ and $B$, from which I formed 2 formulae: $f_1: (\lnot A) \land (\lnot B)$ $f_2: (\lnot A) \lor (\lnot B)$ Are $f_1$ and $f_2$ equivalent?
Coder's user avatar
  • 141
6 votes
2 answers
500 views

Has any schema-agnostic database engine been implemented?

Has any schema-agnostic database engine been implemented?
Leo's user avatar
  • 111
3 votes
3 answers
466 views

How could human behavior and relationships be implemented? [closed]

One of the most compelling issues regarding AI would be in behavior and relationships. What are some of the methods to address this? For example, friendship, or laughing at joke? The concept of ...
user avatar
10 votes
2 answers
545 views

How can an AI system develop its domain knowledge? Is there more than just Machine Learning?

So machine learning allows a system to be self-automated in the sense that it can predict the future state based on what it has learned so far. My question is: Are machine learning techniques the only ...
Jake Marry's user avatar
7 votes
2 answers
478 views

How would "wisdom" be defined in AI?

For years, I have been dealing with (and teaching) Knowledge Representation and Knowledge Representation languages. I just discovered that in another community (Information Systems and the such) there ...
yannis's user avatar
  • 171
12 votes
2 answers
670 views

Is anybody still using Conceptual Dependency Theory?

Roger Schank did some interesting work on language processing with Conceptual Dependency (CD) in the 1970s. He then moved somewhat out of the field, being in Education these days. There were some ...
Oliver Mason's user avatar
  • 5,332
3 votes
1 answer
58 views

Are there emergent models of time in robots?

I am interested in the emergence of properties in agents, and, more generally in robotics. I was wondering if there is work on the emergence of time-related concepts, on the low-level representation ...
Luis's user avatar
  • 538