Search Results

Search found 18628 results on 746 pages for 'artificial neural network'.

Page 72/746 | < Previous Page | 68 69 70 71 72 73 74 75 76 77 78 79  | Next Page >

  • Mathematics for AI/Machine learning ?

    - by Ankur Gupta
    I intend to build a simple recommendation systems for fun. I read a little on the net and figured being good at math would enable on to build a good recommendation system. My math skills are not good. I am willing to put considerable efforts and time in learning maths. Can you please tell me what mathematics topics should I cover? Also if any of you folks can point me to some online material to learn from it would be great. I am aware of MIT OCW, book like collective intelligence. Math Topics to cover and from where to read would really help.

    Read the article

  • TicTacToe strategic reduction

    - by NickLarsen
    I decided to write a small program that solves TicTacToe in order to try out the effect of some pruning techniques on a trivial game. The full game tree using minimax to solve it only ends up with 549,946 possible games. With alpha-beta pruning, the number of states required to evaluate was reduced to 18,297. Then I applied a transposition table that brings the number down to 2,592. Now I want to see how low that number can go. The next enhancement I want to apply is a strategic reduction. The basic idea is to combine states that have equivalent strategic value. For instance, on the first move, if X plays first, there is nothing strategically different (assuming your opponent plays optimally) about choosing one corner instead of another. In the same situation, the same is true of the center of the walls of the board, and the center is also significant. By reducing to significant states only, you end up with only 3 states for evaluation on the first move instead of 9. This technique should be very useful since it prunes states near the top of the game tree. This idea came from the GameShrink method created by a group at CMU, only I am trying to avoid writing the general form, and just doing what is needed to apply the technique to TicTacToe. In order to achieve this, I modified my hash function (for the transposition table) to enumerate all strategically equivalent positions (using rotation and flipping functions), and to only return the lowest of the values for each board. Unfortunately now my program thinks X can force a win in 5 moves from an empty board when going first. After a long debugging session, it became apparent to me the program was always returning the move for the lowest strategically significant move (I store the last move in the transposition table as part of my state). Is there a better way I can go about adding this feature, or a simple method for determining the correct move applicable to the current situation with what I have already done?

    Read the article

  • Another StackOverflow website?

    - by Betamoo
    It seems that StackOverflow is more concerned about programming techniques and coding skills (which is a good thing!).. But I am asking if anyone knows another "StackcOverflow"-like site, but which is mainly concerned about Machine Learning and AI? BTW: I have asked this question after nearly a week without an answer for Question

    Read the article

  • AI testing framework

    - by Jon
    I am looking at developing an AI player for a simple game I have created in C#. I will be creating a population of the bots and evolving them over generations. What I was wondering is there any frameworks out there that could be good for this sort of testing / development. Ideally I would like something that I could plug any / some type of games into and say, OK so have a population of X run it over Y generations and chart the results for me. I was having a think about how I would create something that would do this for me and allow me to reuse this later for different AI projects and all I could think of was to have some sort of core code and some interface contracts that the game and AI would use so that the server can script it. What are your thoughts, does anyone have any practical experience of this sort of thing?

    Read the article

  • Is there any open source AI engine?

    - by Andrei Savu
    I am searching for an open source AI engine implemented in C/C++, ActionScript or Java with no success. Do you know any open source implementation? Update: Thanks for answers! I had no idea how vast the AI field is. I am working on a sample application. I want to add intelligent behavior over a physics engine. I need some sort ai engine designed for games.

    Read the article

  • Why is Lisp used for AI?

    - by Cristián Romo
    I've been learning Lisp to expand my horizons because I have heard that it is used in AI programming. After doing some exploring, I have yet to find AI examples or anything in the language that would make it more inclined towards it. Was Lisp used in the past because it was available, or is there something that I'm just missing?

    Read the article

  • Prolog: Finding the Nth Element in a List

    - by Thomas
    I am attempting to locate the nth element of a List in Prolog. Here is the code I am attempting to use: Cells = [OK, _, _, _, _, _] . ... next_safe(_) :- facing(CurrentDirection), delta(CurrentDirection, Delta), in_cell(OldLoc), NewLoc is OldLoc + Delta, nth1(NewLoc, Cells, SafetyIdentifier), SafetyIdentifier = OK . Basically, I am trying to check to see if a given cell is "OK" to move into. Am I missing something?

    Read the article

  • Counting Sublist Elements in Prolog

    - by idea_
    How can I count nested list elements in prolog? I have the following predicates defined, which will count a nested list as one element: length([ ], 0). length([H|T],N) :- length(T,M), N is M+1. Usage: ?- length([a,b,c],Out). Out = 3 This works, but I would like to count nested elements as well i.e. length([a,b,[c,d,e],f],Output). ?- length([a,b,[c,d,e],f],Output). Output = 6

    Read the article

  • Identifying voice as male or female

    - by duder
    I'm not much into audio engineering, so please be easy on me. I'm receiving an audio file as input, and need to detect whether the speaker is male or female. Any ideas how to go about doing this? I'm using php, but am open to using other languages, and don't mind learning a little bit of sound theory as long as the time is proportionate to the task.

    Read the article

  • Improved Genetic algorithm for multiknapsack problem

    - by user347918
    Hello guys, Recently i've been improving traditional genetic algorithm for multiknapsack problem. So My Improved Genetic Algorithm is working better then Traditional Genetic Algorithm. I tested. (i used publically available from OR-Library (http://people.brunel.ac.uk/~mastjjb/jeb/orlib/mknapinfo.html) were used to test the GAs.) Does anybody know other improved GA. I wanted to compare with other improved genetic algorithm. Actually i searched in internet. But couldn't find good algorithm to compare.

    Read the article

  • Searching in graphs trees with Depth/Breadth first/A* algorithms

    - by devoured elysium
    I have a couple of questions about searching in graphs/trees: Let's assume I have an empty chess board and I want to move a pawn around from point A to B. A. When using depth first search or breadth first search must we use open and closed lists ? This is, a list that has all the elements to check, and other with all other elements that were already checked? Is it even possible to do it without having those lists? What about A*, does it need it? B. When using lists, after having found a solution, how can you get the sequence of states from A to B? I assume when you have items in the open and closed list, instead of just having the (x, y) states, you have an "extended state" formed with (x, y, parent_of_this_node) ? C. State A has 4 possible moves (right, left, up, down). If I do as first move left, should I let it in the next state come back to the original state? This, is, do the "right" move? If not, must I transverse the search tree every time to check which states I've been to? D. When I see a state in the tree where I've already been, should I just ignore it, as I know it's a dead end? I guess to do this I'd have to always keep the list of visited states, right? E. Is there any difference between search trees and graphs? Are they just different ways to look at the same thing?

    Read the article

  • Do you think the AI industry will ever come back?

    - by Isaiah
    I just spent some time reading about the collapse of the AI industry and realized a lot of the reason it failed was because technology was slow to catch up with their theories on when it would be available. I also read that it is believed computers that will be able to emulate human synapses may be made round 2015-2025. It's 2010 now and were getting pretty close to that time frame. I was wondering if anyone thinks that the AI industry will return as the technology lands? And if so, will it change the language market? Could Lisp like languages suddenly experience a burst of growth if it does? Idk I just thought it was interesting thinking about it.

    Read the article

  • Which langauge should i use for Artificail intelligence on web projects

    - by Mirage
    I have to do one project for my thesis involving Artificail intelligence , collaborative filtering and machine learning methods. I only know PHP/mysq/JS and there is not much AI stuff examples in PHP. There are some books on AI on internet but they use Java , Python. Now i have to apply AI techniques on web application. WHich language should i choose java or python. I searhed on internet that i can call java classes inside my php so that can help as as i am very good at php i have also seen that python can also be used with php as well So which way should i go and roughly how much it will take me to learn java i have done java basics but that was 6 years ago

    Read the article

  • Measuring the performance of classification algorithm

    - by Silver Dragon
    I've got a classification problem in my hand, which I'd like to address with a machine learning algorithm ( Bayes, or Markovian probably, the question is independent on the classifier to be used). Given a number of training instances, I'm looking for a way to measure the performance of an implemented classificator, with taking data overfitting problem into account. That is: given N[1..100] training samples, if I run the training algorithm on every one of the samples, and use this very same samples to measure fitness, it might stuck into a data overfitting problem -the classifier will know the exact answers for the training instances, without having much predictive power, rendering the fitness results useless. An obvious solution would be seperating the hand-tagged samples into training, and test samples; and I'd like to learn about methods selecting the statistically significant samples for training. White papers, book pointers, and PDFs much appreciated!

    Read the article

  • Correct formulation of the A* algorithm

    - by Eli Bendersky
    Hello, I'm looking at definitions of the A* path-finding algorithm, and it seems to be defined somewhat differently in different places. The difference is in the action performed when going through the successors of a node, and finding that a successor is on the closed list. One approach (suggested by Wikipedia, and this article) says: if the successor is on the closed list, just ignore it Another approach (suggested here and here, for example) says: if the successor is on the closed list, examine its cost. If it's higher than the currently computed score, remove the item from the closed list for future examination. I'm confused - which method is correct ? Intuitively, the first makes more sense to me, but I wonder about the difference in definition. Is one of the definitions wrong, or are they somehow isomorphic ?

    Read the article

  • How to program simple chat bot AI?

    - by Larsenal
    I want to build a bot that asks someone a few simple questions and branches based on the answer. I realize parsing meaning from the human responses will be challenging, but how do you setup the program to deal with the "state" of the conversation? EDIT: It will be a one-to-one conversation between a human and the bot.

    Read the article

  • large test data for knapsack problem

    - by user347918
    i am researcher student. I am searching large data for knapsack problem. I wanted test my algorithm for knapsack problem. But i couldn't find large data. I need data has 1000 item and capacity is no matter. The point is item as much as huge it's good for my algorithm. Is there any huge data available in internet. Does anybody know please guys i need urgent.

    Read the article

  • Finding patterns in Puzzle games.

    - by José Joel.
    I was wondering, which are the most commonly used algorithms applied to finding patterns in puzzle games conformed by grids of cells. I know that depends of many factors, like the kind of patterns You want to detect, or the rules of the game...but I wanted to know which are the most commonly used algorithms in that kind of problems... For example, games like columns, bejeweled, even tetris. I also want to know if detecting patterns by "brute force" ( like , scanning all the grid trying to find three adyacent cells of the same color ) is significantly worst that using particular algorithms in very small grids, like 4 X 4 for example ( and again, I know that depends of the kind of game and rules ...) Which structures are commonly used in this kind of games ?

    Read the article

  • How to store visited states in iterative deepening / depth limited search?

    - by colinfang
    Update: Search for the first solution. for a normal Depth First Search it is simple, just use a hashset bool DFS (currentState) = { if (myHashSet.Contains(currentState)) { return; } else { myHashSet.Add(currentState); } if (IsSolution(currentState) return true; else { for (var nextState in GetNextStates(currentState)) if (DFS(nextState)) return true; } return false; } However, when it becomes depth limited, i cannot simply do this bool DFS (currentState, maxDepth) = { if (maxDepth = 0) return false; if (myHashSet.Contains(currentState)) { return; } else { myHashSet.Add(currentState); } if (IsSolution(currentState) return true; else { for (var nextState in GetNextStates(currentState)) if (DFS(nextState, maxDepth - 1)) return true; } return false; } Because then it is not going to do a complete search (in a sense of always be able to find a solution if there is any) before maxdepth How should I fix it? Would it add more space complexity to the algorithm? Or it just doesn't require to memoize the state at all. Update: for example, a decision tree is the following: A - B - C - D - E - A | F - G (Goal) Starting from state A. and G is a goal state. Clearly there is a solution under depth 3. However, using my implementation under depth 4, if the direction of search happens to be A(0) -> B(1) -> C(2) -> D(3) -> E(4) -> F(5) exceeds depth, then it would do back track to A, however E is visited, it would ignore the check direction A - E - F - G

    Read the article

  • Is it possible to "learn" a regular expression by user-provided examples?

    - by DR
    Is it possible to "learn" a regular expression by user-provided examples? To clarify: I do not want to learn regular expressions. I want to create a program which "learns" a regular expression from examples which are interactively provided by a user, perhaps by selecting parts from a text or selecting begin or end markers. Is it possible? Are there algorithms, keywords, etc. which I can Google for? EDIT: Thank you for the answers, but I'm not interested in tools which provide this feature. I'm looking for theoretical information, like papers, tutorials, source code, names of algorithms, so I can create something for myself.

    Read the article

  • 3D and AI basics. The foundation before the coding.

    - by Allan
    Hi, everyone. (If you have the time and patience:) I've recently made the decision to study programming seriously and I'm about to order TAOCP and Concrete Mathematics to begin my studies (please don't get caught up on this). I'm very much interested in learning and understanding how 3D works but I'm aware that if I plan to do it right there's still a long walk before I get to actually play with 3D coding. Now to the question.. (tl;dr) Excluding programming itself, what disciplines do I have to be familiar with to code 3D? What kinds of mathematics? Physics? What else? What books do you recommend on such subjects? Now read it all again but replacing "3D" with "AI". Please don't recommend computer-specific books. The question is about the foundation to be learned before using the machine. Also, if possible, please keep the list brief; I plan to order one book on each subject but no more than that for now. Excuse me for any English mistakes, it's not my first language. Thank you.

    Read the article

  • C++ AI Design Question

    - by disney
    Hi, I am currently writing a bot for a MMORPG. Though, currently I am stuck at trying to figure out how to nicely implement this. The design problem is related to casting the character spells in the correct order. Here is a simple example to what I need to archieve. It's not related to casting them, but doing it in the correct order. I would know how simply cast them randomly, by checking which skill has not yet been casted, but in right order as being shown in the GUI, not really. note: the skill amount may differ, it's not always 3, maximum 10 though. Charactername < foobar has 3 skills. Skill 1: Name ( random1 ) cooldown ( 1000 ms ) cast duration ( 500 ms ) Skill 2: Name ( random2 ) cooldown ( 1500 ms ) cast duration ( 700 ms ) Skill 3: Name ( random3 ) cooldown ( 2000 ms ) cast duration ( 900 ms ) I don't really know how I could implement this, if anyone has some thoughts, feel free to share. I do know that most of the people don't like the idea of cheating in games, I don't like it either, nor I am actually playing the game, but its an interesting field for me. Thank you.

    Read the article

  • Problems with with A* algorithm

    - by V_Programmer
    I'm trying to implement the A* algorithm in Java. I followed this tutorial,in particular, this pseudocode: http://theory.stanford.edu/~amitp/GameProgramming/ImplementationNotes.html The problem is my code doesn't work. It goes into an infinite loop. I really don't know why this happens... I suspect that the problem are in F = G + H function implemented in Graph constructors. I suspect I am not calculate the neighbor F correclty. Here's my code: List<Graph> open; List<Graph> close; private void createRouteAStar(Unit u) { open = new ArrayList<Graph>(); close = new ArrayList<Graph>(); u.ai_route_endX = 11; u.ai_route_endY = 5; List<Graph> neigh; int index; int i; boolean finish = false; Graph current; int cost; Graph start = new Graph(u.xMap, u.yMap, 0, ManhattanDistance(u.xMap, u.yMap, u.ai_route_endX, u.ai_route_endY)); open.add(start); current = start; while(!finish) { index = findLowerF(); current = new Graph(open, index); System.out.println(current.x); System.out.println(current.y); if (current.x == u.ai_route_endX && current.y == u.ai_route_endY) { finish = true; } else { close.add(current); neigh = current.getNeighbors(); for (i = 0; i < neigh.size(); i++) { cost = current.g + ManhattanDistance(current.x, current.y, neigh.get(i).x, neigh.get(i).y); if (open.contains(neigh.get(i)) && cost < neigh.get(i).g) { open.remove(open.indexOf(neigh)); } else if (close.contains(neigh.get(i)) && cost < neigh.get(i).g) { close.remove(close.indexOf(neigh)); } else if (!open.contains(neigh.get(i)) && !close.contains(neigh.get(i))) { neigh.get(i).g = cost; neigh.get(i).f = cost + ManhattanDistance(neigh.get(i).x, neigh.get(i).y, u.ai_route_endX, u.ai_route_endY); neigh.get(i).setParent(current); open.add(neigh.get(i)); } } } } System.out.println("step"); for (i=0; i < close.size(); i++) { if (close.get(i).parent != null) { System.out.println(i); System.out.println(close.get(i).parent.x); System.out.println(close.get(i).parent.y); } } } private int findLowerF() { int i; int min = 10000; int minIndex = -1; for (i=0; i < open.size(); i++) { if (open.get(i).f < min) { min = open.get(i).f; minIndex = i; System.out.println("min"); System.out.println(min); } } return minIndex; } private int ManhattanDistance(int ax, int ay, int bx, int by) { return Math.abs(ax-bx) + Math.abs(ay-by); } And, as I've said. I suspect that the Graph class has the main problem. However I've not been able to detect and fix it. public class Graph { int x, y; int f,g,h; Graph parent; public Graph(int x, int y, int g, int h) { this.x = x; this.y = y; this.g = g; this.h = h; this.f = g + h; } public Graph(List<Graph> list, int index) { this.x = list.get(index).x; this.y = list.get(index).y; this.g = list.get(index).g; this.h = list.get(index).h; this.f = list.get(index).f; this.parent = list.get(index).parent; } public Graph(Graph gp) { this.x = gp.x; this.y = gp.y; this.g = gp.g; this.h = gp.h; this.f = gp.f; } public Graph(Graph gp, Graph parent) { this.x = gp.x; this.y = gp.y; this.g = gp.g; this.h = gp.h; this.f = g + h; this.parent = parent; } public List<Graph> getNeighbors() { List<Graph> aux = new ArrayList<Graph>(); aux.add(new Graph(x+1, y, g,h)); aux.add(new Graph(x-1, y, g,h)); aux.add(new Graph(x, y+1, g,h)); aux.add(new Graph(x, y-1, g,h)); return aux; } public void setParent(Graph g) { parent = g; } } Little Edit: Using the System.out and the Debugger I discovered that the program ALWAYS is check the same "current" graph, (15,8) which is the (u.xMap, u.yMap) position. Looks like it keeps forever in the first step.

    Read the article

  • Less Mathematical Approaches to Machine Learning?

    - by Ed
    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 thing I know about PDEs is that they use that funny looking character). This strikes me as odd considering that mathematics itself is a hard thing to "learn." Are there any branches of Machine Learning that use different approaches? I would think that a approaches relying more on logic, memory, construction of unfounded assumptions, and over-generalizations would be a better way to go, since that seems more like the way animals think. Animals don't (explicitly) calculate probabilities and statistics; at least as far as I know.

    Read the article

< Previous Page | 68 69 70 71 72 73 74 75 76 77 78 79  | Next Page >