Stack Exchange
log in sign up chat discuss faq users badges

Area 51 » Science

definition commitment beta

81 Example Questions (4 closed)

active newest votes
up vote 6 down vote
How do you simulate emotional desicion-making within an AI?
added by Tariq Ali Apr 10 '16 at 16:12
link
up vote 4 down vote
Can a single neural network efficiently detect two types of objects in images, or would splitting it into two smaller networks work better?
added by SF. Mar 30 '16 at 12:20
link
example: locating square and rectangular licence plates on photos of cars. – SF. Mar 30 '16 at 12:21
up vote 3 down vote
Could we create an AI with True Language understanding without teaching it about the physical world?
added by JeD Mar 20 '16 at 17:50
link
up vote 3 down vote
How does AI process language, and correctly pronounce words in real-time?
added by KKZiomek Apr 28 '16 at 2:54
link
up vote 2 down vote
Will AI programs eventually be able to write their own programs/subroutines in response to a need/requirement?
added by nsandersen Apr 16 '16 at 14:53
link
(I think it is a question of how complicated code/logic and at what future point.) – nsandersen Apr 16 '16 at 14:54
up vote 1 down vote
How can pre-trained AI algorithms be fixed when they fail to perform as expected? [closed]
added by James Jan 7 '16 at 18:37
link

closed as not a real question by Robert Cartaino Apr 8 '16 at 15:29

It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form.
up vote 1 down vote
What are the advantages of using a convolutionary neural net versus boltsman machines? [closed]
added by dorien, edited by Gwenn Apr 24 '16 at 6:48
link

closed as duplicate of What are the advantages of using a convolutionary neural net versus boltsman machines? by Surb, Robert Cartaino Apr 24 '16 at 14:32

This question covers exactly the same ground as another question in this proposal.
up vote 1 down vote
How can I get a program to "evolve"? [closed]
added by x-x Mar 31 '16 at 1:52
link

closed as not a real question by Robert Cartaino Apr 8 '16 at 15:29

It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form.
up vote 1 down vote
What is the most sample efficient reinforcement learning algorithm?
added by rcpinto Apr 4 '16 at 0:41
link
up vote 1 down vote
Isn't current AI just a computer-specific application of the broader topic of statistics?
added by Nathan Apr 6 '16 at 23:22
link
up vote 1 down vote
Why @TayandYou became crazy and which techniques can prevent those kind of undesired behaviors?
added by rnrneverdies Apr 7 '16 at 23:39
link
up vote 1 down vote
Motivating "Neural Turing Machines". what are "Neural Turing Machines" good for? What this definition is trying to achieve?
added by Matt Carmona G Apr 15 '16 at 2:20
link
up vote 0 down vote
What are the pros and cons of applying pointwise mutual information on a word cooccurrence matrix before SVD?
added by Franck Dernoncourt Jan 6 '16 at 3:03
link
up vote 0 down vote
Should I normalize word2vec's word vectors before using them?
added by Franck Dernoncourt Jan 6 '16 at 3:04
link
up vote 0 down vote
How do we create a neural network to perform arithmetic calculations like a human does? [closed]
added by user Mar 2 '16 at 12:58
link

closed as duplicate of Is it possible to train AI to solve math problems? by Robert Cartaino Apr 8 '16 at 15:32

This question covers exactly the same ground as another question in this proposal.
up vote 0 down vote
Are there any modern alternatives to the abandoned project 3DVCE that allowed for evolution of 3D creatures?
added by Raven Mar 24 '16 at 5:20
link
up vote 0 down vote
How do humans determine if an entity is 'intelligent' if humans also disagree on the definition of 'intelligence'?
added by Tariq Ali Mar 28 '16 at 0:21
link
up vote 0 down vote
What are the advantages of using a convolutionary neural net versus boltsman machines?
added by dorien, edited by wythagoras May 5 '16 at 8:42
link
up vote 0 down vote
What is the definition of 'intelligence' and how do we apply it to machines?
added by Alberto Apr 2 '16 at 16:23
link
up vote 0 down vote
How can we use clustering for doing regression?
added by rcpinto Apr 4 '16 at 0:39
link
up vote 0 down vote
Can autoencoders be used for missing value imputation?
added by rcpinto Apr 4 '16 at 0:40
link
up vote 0 down vote
Could deep learning benefit from using RBF neurons?
added by rcpinto Apr 4 '16 at 0:42
link
up vote 0 down vote
Are Event Correlators considered a branch of AI?
added by SF. Apr 5 '16 at 9:43
link
up vote 0 down vote
How the idea of wages and threshold compares to human learning?
added by enedil Apr 9 '16 at 19:30
link
up vote 0 down vote
Why does automatic translation sometimes (or often) give very usable results and sometimes plainly wrong or silly results?
added by lucvoo Apr 10 '16 at 17:45
link
up vote 0 down vote
How large would a neural net need to be to start displaying complex behavior.
added by ratchet freak Apr 12 '16 at 13:24
link
I'll grant that "complex" is under-defined here. Especially because how little you need for turing completeness. – ratchet freak Apr 12 '16 at 13:25
1  
Maybe fix the question to be "How large would a neural net need to be to be turing-complete?" – Tariq Ali Apr 13 '16 at 13:02
up vote 0 down vote
Does the NAO robot count as artificial intelligence?
added by wizzwizz2 Apr 26 '16 at 17:43
link
You could use a machine-learning algorithm to interface with the NAO robot, I suppose, but the NAO robot is just a robot. Any software running on it is not the NAO robot, but is a program interfacing with the NAO robot. aldebaran.com/en/cool-robots/nao – wizzwizz4 Apr 26 '16 at 18:03
On the other hand, many people use the term "robot" to refer to software and algorithms without any physical form (see "chatterbots" as an example). Those software and algorithms can be said to be 'artificial intelligence'. It's possible that people "assume" that if an algorithm is intelligent, it is therefore a bot. But probably not the other way around (an actual "robot" is not intelligent). – Tariq Ali Apr 28 '16 at 12:15
up vote 0 down vote
What's the difference between life, self-awareness and artificial intelligence?
added by Yisela Apr 29 '16 at 12:45
link
up vote 0 down vote
What are the initial mandatory building blocks -technical and behavioral- for developing a customer service bot?
added by Yisela Apr 29 '16 at 12:50
link
up vote 0 down vote
What does a Behavior UX Designer do?
added by Yisela Apr 29 '16 at 12:50
link
up vote 0 down vote
Why do AI labs recruit Research Scientists?
added by Yisela Apr 29 '16 at 12:51
link
up vote 0 down vote
Should AI programs account for 'mutations' as part of their (evolutionary) development?
added by Yisela Apr 29 '16 at 12:53
link
I don't think I expressed this one very well, but the question is something like: "Should AIs mutate randomly?" – Yisela Apr 29 '16 at 12:57
up vote 0 down vote
What is practical difference between `tanh` and `sigmoid` function?
added by enedil May 1 '16 at 18:03
link
up vote 0 down vote
What are advantages of unsupervised learning over supervised one?
added by enedil May 1 '16 at 18:04
link
up vote 0 down vote
How artificial neural networks compare to biological acknowledging current state of science?
added by enedil May 1 '16 at 18:06
link
up vote 0 down vote
Is recursive self-improvement even a "practical possibility" or is it just a theoretical possibility?
added by Pacerier May 4 '16 at 13:20
link
up vote 0 down vote
Is mutation and crossover necessary in genetic algorithm in traveling salesman problem, both does the same thing,ie shuffle the order of city to visit
added by j4rey89 May 4 '16 at 13:21
link
up vote -1 down vote
What's the difference between sigmoid and perceptron neurons?
added by Programmix Mar 20 '16 at 20:05
link
up vote -1 down vote
Will genetic algorithms to get to a desired AI algorithm necessarily inflict pain on some (intermediary) AI versions and therefore be unethical?
added by Count Iblis Mar 21 '16 at 1:11
link
up vote -1 down vote
In case we reach technological singularity, is the fear that machines could take over the world justified?
added by ByteCommander Mar 23 '16 at 9:12
link
1 2 3