18
votes
Accepted
Why do we need common sense in AI?
Commonsense knowledge is the collection of premises that everyone, in a certain context (hence common sense knowledge might be a function of the context), takes for granted. There would exist a lot of ...
- 41.4k
10
votes
Why do we need common sense in AI?
We need this kind of common sense knowledge if we want to get computers to understand human language. It's easy for a computer program to analyse the grammatical structure of the example you give, but ...
- 5,417
5
votes
What roles knowledge bases play now and will play in the future?
First of all, I would like to point out the main differences between knowledge base and (Deep) machine learning, specially when the main focus is on "AI" not "Data Science":
NNs are like a black box; ...
- 405
5
votes
Did Turing foresee the required capabilities to pass the Turing test?
I find it unlikely that you'll find a firm answer, so I will try my best to guide you towards information which may help you form an opinion either way. Turing had the controversial opinion (which ...
- 587
4
votes
What roles knowledge bases play now and will play in the future?
Although asked over 3 years ago, the question is still interesting and while I agree with the original answer, a lot can be added to it.
First, I'd like to point out that the term "knowledge base&...
- 41
4
votes
How would an AI understand grids?
Although it is common to represent a grid as two dimensional array in a computer program, this is not the only way to represent one. You could, for example, use a generalized graph structure made of ...
- 9,392
3
votes
Accepted
As a starter: what is the form of training data for image processing
Your question depends heavily on the method you are using for machine learning. It sounds like you want to extract certain features like "curves and straight lines" from your images and use them as ...
- 1,684
3
votes
Given statements $A$ and $B$, are the formulae $(\lnot A) \land (\lnot B)$ and $(\lnot A) \lor (\lnot B)$ equivalent?
One way of verifying whether two boolean expressions are equivalent is to assign all possibilities to all variables, and comparing all results.
A
B
f1
f2
T
T
F
F
T
F
F
T
F
T
F
T
F
F
T
T
We can ...
- 789
3
votes
How do language models know what they don't know - and report it?
The data it is trained on includes variants of "I don't know". For instance, if you ask me what is the meaning of life and I reply I don't know, then that is the information schema the AI ...
2
votes
How can an AI system develop its domain knowledge? Is there more than just Machine Learning?
Well, we are talking about a system (a machine) which develops knowledge (learns), so it is kind of difficult for such a technique to not fall within machine learning.
But you could argue that ...
- 4,295
2
votes
How would "wisdom" be defined in AI?
As with another answer, I am also skeptical of the distinctions made in the DIKW pyramid.
Nonetheless, a very popular machine learning approach for answering 'Why?' questions is the application of ...
- 7,266
2
votes
What is the difference between logic-based and rule-based AI?
Rule-based systems cover a wide range of systems. Some make use of boolean if/then/else rules, others may use weighting or even probabilistic inference. Some operate on frames, some on java objects, ...
- 121
2
votes
Training an AI to play Starcraft 2 with superhuman level of performance?
StarCraft II is a real time strategy game that combines fast paced micro actions with the need for high level planning and execution. StarCraft II being a popular game with millions of users it ...
- 1,186
2
votes
Accepted
When is a knowledge base consistent?
I will first recapitulate the key concepts which you need to know in order to understand the answer to your question (which will be very simple, because I will just try to clarify what is given as a &...
- 41.4k
2
votes
Accepted
How to mathematically/logically represent the sense of sentences like "The cat drinks milk"?
Let start by classify the phrases you propose:
The cat drinks milk. => action
Sun is yellow. => descriptive/declarative, immutable
I was at work yesterday. => descriptive, time related
1) The ...
- 1,293
2
votes
Why do we need common sense in AI?
I'll answer this question in several parts:
Why do AGI systems need to have common sense?
Humans in the wild reason and communicate using common sense more than they do with strict logic, you can ...
- 2,111
2
votes
Why do we need common sense in AI?
Perhaps it would help to give an example of what can go wrong without common sense: At the start of the novel "The Two Faces of Tomorrow" by James Hogan, a construction supervisor on the Moon files a ...
- 21
2
votes
What is the difference between a semantic network and an ontology?
A semantic network is a way to implement an ontology. An ontology is just a generalised way of representing knowledge in a particular domain, and there are multiple ways of doing so. The key that ...
- 5,417
2
votes
What would be a good internal language for an AI?
This is (even though it doesn't look like it at first glance) a deeply philosophical question about the nature of 'meaning'. This answer is necessarily limited in scope.
There are many ways of ...
- 5,417
2
votes
What would be a good internal language for an AI?
I think the first question you should answer is: "What questions should the AI be able to answer?" If the intend was that the AI should be able to answer any questions, then that is simply not doable (...
- 186
2
votes
What are the differences between a knowledge base and a knowledge graph?
What is a knowledge graph?
Appendix A.3 "Knowledge Graphs": 2012 Onwards of the survey Knowledge Graphs (which is probably the most extensive survey on KGs) states that knowledge graphs have ...
- 41.4k
2
votes
Accepted
Reasoning about 2d spatial square configuration
According to the tree:
"x TPP c" implies "x IntInt c" and "x BndBnd c" and "x BndInt c" and "not x IntBnd c".
"c DC b" implies "not c ...
- 1,293
2
votes
How do language models know what they don't know - and report it?
It makes sense to assume that reinforcement learning from human feedback (RLHF) has some merit, at least. I'll explain myself.
In RL we have a reward (the human feedback), a policy (which should be ...
- 3,186
2
votes
Accepted
Real world example of an Knowledge based system
Knowledge representation is used extensively in the bioinformatics community where ontologies are used to infer classification hierarchies in the annotation of biological data. See for example the ...
- 186
1
vote
Is unsupervised disentanglement really impossible?
The impossibility is referring how to learn the disentangled representations from the observed distribution or to know whether you have a disentangled representation in the first place.
Basically, an ...
- 33.3k
1
vote
Why do we need common sense in AI?
Is this common sense, or is this natural language understanding?
It's been said that natural language understanding is one of the hardest AI tasks. This is one of the examples showing why. The first ...
- 131
1
vote
Are Relational DBs and SQL used in Expert Systems?
A recent research example is the "Grind" system. Take a look at the paper Computing FO-Rewritings in $\mathcal{E} \mathcal{L}$ in Practice: from Atomic to Conjunctive Queries (2018) by Peter ...
1
vote
How to mathematically/logically represent the sense of sentences like "The cat drinks milk"?
People normally represent sentences like this as vectors of a specific length, normally about 2500 in length. The algorithm that can do this is sentence2vec. It is basically a derivative of word2vec. ...
- 873
1
vote
As a starter: what is the form of training data for image processing
I think Demento has answered it well, but probably below can add some more understanding to you.
[1] Usually the data stored for image processing relates to the Image Pixel Densities(as per the many ...
- 291
1
vote
What does Brooks mean by "representation"?
In that paper, Brooks introduced the basis for what became known as his "subsumption architecture". The idea was to get away from the 1980's popular approach of a single global representation of all ...
- 679
Only top scored, non community-wiki answers of a minimum length are eligible