Artifical Intelligence in the field of computer science is the study, design and engineering of intelligent systems able to perceive their environment and take actions to optimize their chance of success in achieving a goal.

learn more… | top users | synonyms (1)

2
votes
1answer
64 views

To what values should you initialize the neurons and connection strengths in a neural network?

The values of all of the neurons in my neural network are initialized to 0 and the connection strengths between the neurons are set to randomly generated floats, between 0 and 1. I have seen other ...
2
votes
1answer
57 views

How can you write an activation function in a neural network to handle a layer architecture of arbitrary dimensions?

I am making a neural network in Clojure that can take an array of integers,and return a data structure representing the layers of a neural network: so (make-layers [1 4 5]) would evaluate to: [[0] ...
3
votes
1answer
110 views

Names for the two types of AI (in my eyes)?

In my head, AI attempts get sorted into two categories. I'm wondering if the distinction is present in reality or just my imagination. If this it's real, I'd like to know of any terms for them. The ...
-1
votes
1answer
48 views

What is the difference between multi-label learning and multi-label classification? [closed]

The litterature on multi-label learning uses the terms: multi-label learning and multi-label classification. I was wondering what the difference between these terms is, and when to use one over the ...
4
votes
2answers
59 views

How should dynamic, interruptible multitasking structure look like?

I am trying to make an AI that plays a game. Actually, I'm playing around with both StarCraft and MineCraft which are completely different kinds of games. As well, I use different programming ...
3
votes
2answers
168 views

Obstacle bypass in 2d environment

For this 2d grid (black square are not penetrable, white square are): I want to find path who permit to move an object to a start point (x:18, y:18) to a end point (x:1, y:1), square by square. ...
0
votes
1answer
126 views

How to avoid loop in a dept-search in a graph?

I must implement , in Lisp , a depth-search algorithm in an implict graph (namely a graph where I have the starting node, the goal node, and the successor function ,f, that give a node create his ...
-1
votes
1answer
79 views

How probability function is computed for the game Battleships? [closed]

I'm writing AI for the game and encountered this article that helped me out. I'm not sure how the probability function is computed. Does it rely on some advanced math I'm not understanding or for each ...
0
votes
1answer
111 views

Artificial intelligence decision making [closed]

So I am working on a artificial intelligent assistant that is supposed to help you making correct decision when playing the game domino. Basic rules: http://www.pagat.com/tile/wdom/caribbean.html As ...
1
vote
0answers
46 views

How to evaluate a recurrent connection in an artificial neural network?

I just can't understand how should I compute the output of a neural network, which contains a recurrent connection. So here is an example: (i_1,2 are the input values, w_1,2,3,r are the ...
1
vote
0answers
43 views

Can't figure out how to parallelize the calculation of the amount of offspring expected for species in genetic algorithm

I developed a genetic algorithm in java 8 taking advantage of its reasonably free parallelism opportunities with Streams. As you are likely aware, running the epochs takes its time for even a test ...
1
vote
1answer
51 views

What is the Discount Factor for in the Value Iteration Algorithm? [closed]

Can someone please explain what the discount factor means in the Value Iteration Algorithm for solving Markov Decision Processes? I understand the equation, but I don't understand why it requires ...
5
votes
2answers
188 views

Clustering algorithm

I have a set of n elements (1,000 <= n <= 100,000) and I can compute the grade of similarity between each pair, that is a value from 0 (very similar) to 1 (very different). I would like to ...
3
votes
2answers
248 views

Best practice A.I. - check all possible moves or pick an objective?

I'm looking for some general guidance on how to produce best practice A.I. The way I understand it, the way A.I. works for games like Go, Chess etc is by considering all possible moves (combinations ...
2
votes
1answer
167 views

Enemy AI for classic game Bubble Bobble [closed]

I am building a similar game to Bubble Bobble. This is the scenario: where E represents enemies, and P represents the player. If a user falls through the lower hole, it reappears through the ...
2
votes
1answer
135 views

Tree search for path finding - algorithm critiques

So, I'm pretty new to AI in general, and am trying to implement a tree-based search from a textfile input (a maze). An example would be: |||||||||||||||||||||| | || | | | \ | |||||| ...
2
votes
1answer
145 views

Why are heuristics a disadvantage for decidable problems?

I'm reading Introduction to Artificial Intelligence by Ertel. This line has me stumped from the textbook (page 102): For decidable problems such as the 8-puzzle this means that the whole search ...
11
votes
1answer
540 views

Efficient way to represent hexagonal board logic for abalone-like games

I have to implement the AI for Abalone game and I'm wondering what is the best way to represent the board logic using Java without wasting too much resources in all checks and updates routines ...
1
vote
0answers
90 views

Neural network converges to 0.5 for XoR

I'm coding a neural network in C for an OCR project. Before testing with character recognition, I'm making it learn the XoR operation. Although, the results I'n getting always converges to 0.5 instead ...
-1
votes
4answers
284 views

Real AI in a compiled language [closed]

possibly a newbie question here. I heard that if a real AI were to exist it would have to evolve, by that I think it means it should be able to write new code then run itself with the new code. Could ...
10
votes
5answers
2k views

Is it imaginable to teach a machine how to program itself to a defined specification? [closed]

A friend of mine without programming knowledge asked me this question and I found it interesting. I think it is not possible because it would require a really advanced artificial intelligence ...
0
votes
2answers
264 views

Algorithm for figuring out the enemy flag's location in Stratego

I am currently programming a Stratego game in JavaScript, simply because I wanted to learn to use JavaScript while spending some time to keep my programming skills up to par. (My current work ...
2
votes
0answers
94 views

What makes the functional and logic programming paradigms well suited for programming AI? [duplicate]

I have been researching different programming paradigms. I have found a lot of people saying that one of the areas where logic and functional programming are particularly good is programming AI, but I ...
3
votes
2answers
191 views

Ranking players depending on decision making during a game

How would I go about a ranking system for players that play a game? Basically, looking at video games, players throughout the game make critical decisions that ultimately impact the end game result. ...
5
votes
1answer
384 views

Creating New Scripts Dynamically in Lua

Right now this is just a crazy idea that I had, but I was able to implement the code and get it working properly. I am not entirely sure of what the use cases would be just yet. What this code does ...
3
votes
1answer
248 views

Minimize travel distance of n people to n locations

The problem: Given the coordinates of N people on a regular 2-dimensional plane and N target points-of-interest (POI) on the same plane, determine the set of pairs of people and POIs that minimize ...
1
vote
1answer
211 views

How can I apply machine learning to automated melody generation? [closed]

I've been working for a while on an app that makes up melodies. Each melody is composed of several phrases (musical sentences, or 'sub-melodies'). Now, I want to improve on this: The user can press ...
1
vote
0answers
93 views

AI development, variation on the horizon effect

Developing an alpha-beta search for "Colorito", which has the characteristic that sometimes simple hill-climbing is impossible; so a sequence of 2 or 3 moves is the only way to make progress. I came ...
1
vote
2answers
76 views

Determinining “value” in multi-agent microeconomical simulation

I am trying to determine an objective way for a self-interested agent to calculate the optimal buying/selling price for goods in a multi-agent simulation not dissimilar to Sugarscape ...
0
votes
2answers
159 views

Microeconomical simulation: coordination/planning between self-interested trading agents

In a typical perfect-information strategy game like Chess, an agent can calculate its best move by searching the state tree for the best possible move, while assuming that the opponent will also make ...
0
votes
1answer
106 views

Looking for a specific type of artificial intelligence

I am looking to create a challenging AI project. There is an online card game that allows you to build a deck to play with out of randomly presented cards. You have to choose one each time out of a ...
0
votes
2answers
100 views

Could one sample be enough for a perceptron training?

I need to compare a picture and decide whether or not it is similar to another one. In this case, I would like to use a simple perceptron that compares pixelmaps of both pictures. But I have only very ...
3
votes
1answer
178 views

How to do inference in a card game?

In the game there are 5 players, each with 8 cards in hand. No other card is present. Using Monte Carlo (MCTS) I run many simulations of the game from the current state to the end of the match. In ...
3
votes
0answers
199 views

Understanding velocity update in Binary Particle Swarm Optimization

I am wondering how to interpret the velocity update in a Binary Particle Swarm Optimization (PSO). To recap the velocity update : V(t+1) = V(t) + c1 * r1 * (XlocalBest - X(t)) + c2 * ...
1
vote
2answers
309 views

Neural network input preprocessing

It's clear that the effectiveness of a neural network depends strongly on the format you give it to work with. You want to pre-process it into the most convenient form you can algorithmically get to, ...
18
votes
3answers
6k views

Best techniques for an AI of a card game

I’m trying to develop an AI for a card game and I’m a bit stuck about the technique/algorithm I should use. Here are a few assumptions about the game: After the cards are distributed to players, ...
1
vote
1answer
14k views

Algorithm to create an TicTacToe game AI [closed]

What are the algorithms I could use to create an AI for the game TicTacToe. I have already used Alpha–beta pruning and Predictive modelling. What the other good Algorithms I can use to create this AI. ...
5
votes
2answers
316 views

How to solve this problem- Neural Net? Fuzzy? Other?

Hi I have a programming problem that I would like to solve using some artificial intelligence technique. I really dont know where to start. I would like some guidance as to what methodology to pursue. ...
1
vote
0answers
112 views

Algorithm to analyse and predict

I'm having a set of data's, say Question, Question's Main Category,Main Category followers, Question's Related Categories,Each Related Categories followers, Whether it got answer in 24hrs [Yes/No] ...
1
vote
2answers
206 views

Building a tool to fix compiler errors automagically

When a program doesn't compile, error messages are sometimes esoteric. Often a simple Google search leading to a site like stack exchange solves the problem. Now why can't we automate this? How ...
2
votes
2answers
3k views

Getting started with AI (Artificial Intelligence) [closed]

I recently got interested in Artificial Intelligence. In my daily life I am a software engineer at a company that develops mobile apps. I am wondering what is the best way to read up on AI? What are ...
3
votes
1answer
843 views

Getting started with object detection - Image segmentation algorithm

Just getting started on a hobby object-detection project. My aim is to understand the underlying algorithms and to this end the overall accuracy of the results is (currently) more important than ...
5
votes
1answer
437 views

Subsumption architecture vs. perceptual control theory

I'm a new person to AI field and I have to research and compare two different architectures for a thesis I'm writing. Before you scream (homework thread), I've been reading on these two topics only ...
3
votes
1answer
317 views

Algorithm, AI, or intelligent agent suggestions for ingesting poorly-formatted & variable data from different document types

Thanks for looking! Background I have been tasked with writing a program to normalize and ingest data from various sources to a common database. For the sake of simplicity, let's say that the ...
-2
votes
1answer
190 views

How does one generate challenging different puzzles like the one in AirLock android game [closed]

here's the link of the app: https://play.google.com/store/apps/details?id=com.iatll.airlock I had studied AI in the final year of b.tech cs programme, and i do remember some algorithm of ...
2
votes
2answers
297 views

Looking for companies with strong R&D departments, specifically for A.I., but I can't seem to find many. Are there only a handful?

I plan to get a PhD in CS, concentrating in some subfield of artificial intelligence, not sure which one at the moment. I'm looking into R&D departments in industry, but there don't seem to be ...
2
votes
1answer
612 views

Machine Learning with sample data set

I have a question regarding Machine Learning in general. Consider the following scenario: Given a piece of text, we want a program to know whether the text is 'abusive' or not. To do this we can ...
1
vote
1answer
2k views

I don't understand value iteration

In class I am learning about value iteration and markov decision problems, we are doing through the UC Berkley pac-man project, so I am trying to write the value iterator for it and as I understand ...
10
votes
3answers
923 views

Can a neural network provide more than “yes” or “no” answers?

Every example neural network for image recognition I've read about produces a simple "yes" or "no" answer. One exit node corresponds to "Yes, this is a human face," and one corresponds to "No, this ...
3
votes
2answers
294 views

Under which area of Artificial Intelligence is my knowledge store?

I've a maturing idea regarding a knowledge store. For the purposes of this question, the store would be used by a police force for the recording and querying of crimes. I believe that ...