Questions tagged [artificial-intelligence]

Artificial intelligence (AI) is the branch of computer science and technology that studies the development of machines able to simulate aspects of human intelligence. This tag may also refer to the part of a computer game application that controls the behavior of the virtual characters with which the player may interact during the game.

NOTE: If you want to use this tag for a question not directly concerning implementation, then consider posting on Artificial Intelligence, Computer Science, Data Science, or Cross Validated instead; otherwise you're probably off-topic. Please choose one site only and do not cross-post to more than one - see Is cross-posting a question on multiple Stack Exchange sites permitted if the question is on-topic for each site? (tl;dr: no).

Artificial intelligence (AI) is the branch of computer science and technology that studies the development of machines able to simulate aspects of human intelligence. This tag may also refer to the part of a computer game application that controls the behavior of the virtual characters with which the player may interact during the game.

While there are many different definitions, AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success. John McCarthy, who coined the term in 1956, defines it as "the science and engineering of making intelligent machines."

References

The field of artificial intelligence comprises areas as diverse as:

Related Tags

8491 questions
3
votes
2 answers

how to prove a compatible heuristics can be a admissible heuristics in A* search algorithm

compatible heuristics (h) is the one that has below condition: h(n) <= c(n,a,n') + h(n') **************************************************** admissible heuristics (h) is the one that has below condition: 0 <= h(n) <= h*(n) h*(n) is the real…
Vahid Najafi
  • 4,654
  • 11
  • 43
  • 88
3
votes
4 answers

Q learning: Relearning after changing the environment

I have implemented Q learning on a grid of size (n x n) with a single reward of 100 in the middle. The agent learns for 1000 epochs to reach the goal by the following agency: He chooses with probability 0.8 the move with the highest…
3
votes
1 answer

Text clustering within a log file

I am working on a problem of finding similar content in a log file. Let's say I have a log file which looks like this: show version Operating System (OS) Software Software BIOS: version 1.0.10 loader: version N/A kickstart: version…
3
votes
1 answer

Bug in Resilient Backpropagation?

I'm struggling with implementing Resilient Propagation correctly. I already implemented the backpropagation Algorithm to train a Neural Network, and it works as expected for an XOR-Net, i.e. it takes about 600 Epochs to drop Error below 1%. Now i…
3
votes
1 answer

How should I learn NLTK?

NLTK is something I've been interested for a fair while, but I have been so far unaware of an efficient way to become (relatively) acquainted with NLTK. I have done some preliminary research, which has resulted in my awareness of two online…
user2469456
  • 281
  • 1
  • 3
  • 8
3
votes
1 answer

Practical use cases for machine learning algorithms

I am just starting out studying machine learning and currently doing Andrew Ng's course on Coursera. I am going through the course but am a bit lost. It will make studying all those algorithms/theory a lot rewarding if I can see some use cases for…
user220201
  • 4,514
  • 6
  • 49
  • 69
3
votes
2 answers

Back propagation algorithm: error computation

I am currently writing a back propagation script. I am unsure how to go about updating my weight values. Here is an image just to make things simple. My question: How is the error calculated and applied? I do know that k1 and k2 produce error…
basickarl
  • 37,187
  • 64
  • 214
  • 335
3
votes
1 answer

How prolog work as intellegent language?

I have written set of rules in prolog, if rule matches particular action occurs. something like: rule_second_question(X, Y, X, W):- ( LINK_BASE == 'G', is_verb_form(X), aggregate_all(X, linkage(W, _, _, _, _, _, _, _, _,…
puncrazy
  • 349
  • 2
  • 14
3
votes
9 answers

Less Mathematical Approaches to Machine Learning?

Out of curiosity, I've been reading up a bit on the field of Machine Learning, and I'm surprised at the amount of computation and mathematics involved. One book I'm reading through uses advanced concepts such as Ring Theory and PDEs (note: the only…
Ed
3
votes
2 answers

Does the min player in the minimax algorithm play optimally?

In the minimax algorithm, the first player plays optimally, which means it wants to maximise its score, and the second player tries to minimise the first player's chances of winning. Does this mean that the second player also plays optimally to win…
LearningMath
  • 851
  • 4
  • 15
  • 38
3
votes
1 answer

Recognizing patterns in a number sequence

I think this should be an AI problem. Is there any algorithm that, given any number sequence, can find patterns? And the patterns could be abstract as it can be... For example: 12112111211112 ... ( increasing number of 1's separated by 2…
KH Kim
  • 1,155
  • 1
  • 7
  • 14
3
votes
1 answer

How exactly does the dp parameter in the houghcircle function in the opencv library work?

I'm trying to understand the .houghcircles() function and I'm not fully understanding how dp affects the results. Looking up http://docs.opencv.org/modules/imgproc/doc/feature_detection.html?highlight=houghcircles#houghcircles, it says: dp –…
PGT
  • 1,468
  • 20
  • 34
3
votes
1 answer

A* (A star) algorithm not exactly working

I'm trying to implement an A star searching method for a college work, so i kinda need to make it from scratch, but I'm having some trouble making it work the correct way. Here's a picture of my problem: As you can see, it does find a path, but not…
markus
  • 1,011
  • 2
  • 10
  • 17
3
votes
1 answer

Store and compare android sensor(accelerometer) data sets to match the pattern

I am developing android application which will learn and than evaluate aggressive driving behavior i.e. sharp turns, sudden brake etc... As i am trying to make a learning algorithm. My approach now is to get sensor data when wrongly driven and make…
3
votes
1 answer

Is neural net only capable of solving problems with 0..1 input values and 0..1 expected output values?

I've just created my first neural net, which uses gradient method and back propagation learning algorithm. It uses hyperbolic tangent as activation function. The code is well unit tested so I was full of good hopes that the net will actually work.…
Andrzej Gis
  • 13,706
  • 14
  • 86
  • 130