artificial-intelligence

问题 As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance. Closed 7 years ago . I need topic ideas related to AI on which I will base my thesis. I am mostly interested in Genetic Algorithm and Neural Networks

问题 Im trying to do something which seems to be really simple but i cant get my head around. I want to split a list in prolog from given predicates and iterate over the objects. Example: object_properties(jackass, [comedy, -australian]). object_properties(the_godfather, [drama, crime, -character_batman]). How can i iterate over the lists and print it to the screen? More specificaly i need to ask the user if the object has the property. If they say yes move on to the next item in the list, if they

问题 I want to classify the input as one of 3 possibilities. Is it better to use 3 networks with one output each or 1 network with 3 outputs? (i.e. 3 networks that output 0 or 1 or 1 network that outputs a one hot vector of length 3 [1,0,0] Does the answer change depending on how complex the incoming data is to classify? At what amount of outputs does it make sense to partition the networks (if ever)? For example, if I want to classify into 20 groups, does it make a difference? 回答1: I would say it

问题 I have some doubts regarding best first search algorithm. The pseudocode that I have is the following: best first search pseudocode First doubt: is it complete? I have read that it is not because it can enter in a dead end, but I don't know when can happen, because if the algorithm chooses a node that has not more neighbours it does not get stucked in it because this node is remove from the open list and in the next iteration the following node of the open list is treated and the search

问题 I am having issues understanding the algorithm. Here is the most popular one seen online for all members of population sum += fitness of this individual end for for all members of population probability = sum of probabilities + (fitness / sum) sum of probabilities += probability end for loop until new population is full do this twice number = Random between 0 and 1 for all members of population if number > probability but less than next probability then you have been selected end for end

问题 I would like to solve the following problem using constraints but i actually don't know where to begin so i decided to post it here for help. *** Fitting squares *** Given the set of black squares of Figure 1 (a 2x2, 3x3, 4x4 and a 5x5 square), fit them all into the white rectangle of Figure 1 (a 7x9 rectangle), and this in such a way that there is no overlap between the squares. Note that the black squares can only be put on integer coordinates. Formulate the problem above as a constraint

问题 I'm new to SVMs, and I'm trying to use the Python interface to libsvm to classify a sample containing a mean and stddev. However, I'm getting nonsensical results. Is this task inappropriate for SVMs or is there an error in my use of libsvm? Below is the simple Python script I'm using to test: #!/usr/bin/env python # Simple classifier test. # Adapted from the svm_test.py file included in the standard libsvm distribution. from collections import defaultdict from svm import * # Define our sparse

问题 im having a response like below from fann Epochs 1. Current error: 0.2500066161. Bit fail 4. Epochs 58. Current error: 0.0000930788. Bit fail 0. what does Bit fail mean here? 回答1: The bit fail limit is the maximum difference between the expected and actual output neuron value that is allowed.The default bit fail limit is 0.35. If the difference between the expected and actual output neuron value is more that the bit fail limit, this counts as 1 bit fail. In the sample output you gave, at 58

问题 I've been trying objectDetection in openCV.. Followed a few steps.. Resizing it to 64x64 resolution Changing it to gray scale Fetching XML for object detection Drawing rectangle fringing the pattern Yet, I couldn't achieve it.. Here's my code : #include<iostream> #include "cv.h" #include "highgui.h" #include<vector> using namespace cv; using namespace std; int main() { IplImage* img; img = cvLoadImage( "hindi3.jpg" ); vector<cv::Rect> objects; // ***Resize image to 64x64 resolution***

问题 Before starting implementation of solution for my problem I just want to be sure if I will not “reinvent wheel” and if I can reuse work that someone have done before. So my problem is: I have made image matcher using OpenCV library. This matcher receives a set of image files and trying to find similar images in database. At the end it returns statistical results according to ROC Curves definition (True Positive, True Negative, False Positive and False Negative number of matches). These