For questions about artificial intelligence.

learn more… | top users | synonyms

1
vote
2answers
117 views

Neural network cost function - why squared error?

Question: Why is the squared error most often used for training neural networks? Context: Neural networks are trained by adjusting the link weights. The key factor that informs these adjustments is ...
4
votes
1answer
176 views

State space for 8-queen problem

While reading Artificial Intelligence a Modern Approach I came across the following formulation for the 8-queen problem: Initial state: No queens on the board. States: Arrangements of n queens (0 &...
4
votes
1answer
1k views

Convert a WFF to Clausal Form

I'm given the following question: Convert the following WFF into clausal form: \begin{equation*} \forall(X)(q(X)\to(\exists(Y)(\neg(p(X,Y)\vee r(X,Y))\to h(X,Y))\wedge f(X))) \end{equation*} ...
3
votes
1answer
182 views

$i,j,k$ Values of the $\Theta$ Matrix in Neural Networks

SO I'm looking at these two neural networks and walking through how the $ijk$ values of $\Theta$ correspond to the layer, the node number. Either there are redundant values or I'm missing how the ...
2
votes
1answer
44 views

What aspects of convex optimization are used in artificial intelligence, if any?

I work on convex optimization with Stephen Boyd's book. As an example, support vector machines are mentioned as an application of separating hyperplanes theorem. I am wondering if there is any other ...
2
votes
1answer
41 views

Comparing two textbooks for machine learning

I am a Ph.D student in Electrical Engineering. I am going to study the field of machine learning and I found some textbooks to study this field. 1) Probabilistic Graphical Models: Principles and ...
2
votes
1answer
264 views

Gradient descent/ nonlinear optimization intuition needed

all. I'm taking an introductory AI class, and we're using the gradient descent algorithm to find the optimized/ lowest cost of a set of thetas (variable coefficients) to best fit a regression line. In ...
1
vote
1answer
25 views

How to find the optimal linear basis functions of an MDP?

Given a set of basis functions, there are many papers on finding a weight vector to linearly approximate the value function. Is there any paper on how to find the basis functions? Is it possible to ...
0
votes
1answer
27 views

who is lying? - by using Knowledge Base by resolution

I found this question online, and tryied to solve. However, I have trouble with the methods Here question Three children Allison, Jack, and Frank were playing “hide and seek” game in an apartment. ...
0
votes
1answer
36 views

Dung's Argumentation Framework

Given an extension of Dung's argumentation framework, and all definitions therein, let $$AF_1 = \langle A,Def \rangle$$ be a framework where $$A = \{ A, B, C, D, E, F, G, H \}$$ and $$Def = \{A def G, ...
0
votes
1answer
143 views

binary resolution rule proof

I want to proof the binary resolution rule that is, if we For any two clauses $C_1$ and $C_2$, if there is a literal $L_1$ in $C_1$ that is complementary to a literal $L_2$ in $C_2$, then delete $L_1$ ...
0
votes
1answer
69 views

Bayesian Nets. No active path from X to Y, versus No inactive paths from X to Y

I am learning d-seperation in Bayes nets for my A.I. class. What this involves is considering all paths from some node X to Y (representing random variables) and seeing whether such paths are active ...
0
votes
1answer
47 views

probabilistic behaviour

I am trying to understand what 'probabilistic behaviour' in a 'deterministic model' means. I am reading this paper http://www.ulb.ac.be/sciences/use/publications/JLD/16.pdf but i find myself unable ...
3
votes
0answers
437 views

Modern Mathematical Theory for Neural Networks, Cellular Automata, Neuroscience

Is it possible for someone to do research on subjects like neural networks, cellular automata, or neuroscience as an applied mathematician? I have in mind the theoretical development of these fields,...
2
votes
0answers
42 views

maximizing alpha-beta puning.

I was searching a more pertinent place to post artificial intelligence concerned question, but some results pointed me to similar questions posted here, thus I chose math.se, now let's get through ...
2
votes
0answers
86 views

How to Calculate Values from Incoming Messages? - Evidence Propagation in Bayesian Network

I'm currently trying to wrap my head around evidence propagation in bayesian network (simple tree propagation) but I'm having trouble finding information about the process. As an example, let's take ...
1
vote
0answers
30 views

AI Parameters for Tetris-like Game

I am building an AI to play a variation of Tetris. The rules are changed in that there are 19 different types of pieces, rotation is not allowed, and the pieces can be placed anywhere in a 10X10 grid. ...
1
vote
0answers
26 views

The significance of odds and logs in Bayes Naive Classification

I do understand the concept of Naive Bayesian classification, as it tries to calculate the probability of an outcome of a class given multiple evidences. It comes from the Bayes theorem and it is ...
1
vote
0answers
39 views

Is normalized RBF always better than RBF

The question is as the title. Mathematically, I want to know does the following inequation always hold for any vector $\mathbf b$? $\mathbf b^T \mathbf B \mathbf B^+ \mathbf b \, \ge \, \mathbf b^T \...
1
vote
0answers
20 views

Implicit feature space of Power Kernel

For the polynomial kernel, $K(x,y) = (x^Ty+c)^d$, the implicit feature space $\phi$ for which $K(x,y) = \phi(x)^T \phi(y)$ is of finite dimension and well known [1][2]. It is also well known that the ...
1
vote
0answers
38 views

Improving Simulated Annealing based on Measure of Goodness

can anyone answer this question or direct me to a reference that can help? Simulated Annealing returns the current state when the end of the annealing schedule is reached and if the annealing ...
1
vote
0answers
48 views

Complexity analysis of alpha beta pruning of a full tree

I am trying to understand the derivation of a time complexity for an alpha-beta pruning algorithm but up till now have not found any reasonable recourse. Many recourses claim that if you take a full ...
1
vote
0answers
55 views

feature selection for continuous variables

I wonder how exactly "feature selection" should be performed in case of continuous feature values. When feature values are discrete it is very straitforward to apply feature selection, but what to do ...
1
vote
0answers
77 views

Solomonoff induction , Shannon Entropy, Kolmogorov Complexity.

If Expected Kolmogorov Complexity equals Shannon Entropy why can't Shannon Entropy be used as an approximation of Kolmogorov Complexity in Solomonoff Induction? Regarding Kolmogorov Complexity and ...
1
vote
0answers
344 views

Estimating conditional probability as a function of time

My question relates to estimating from a time series a time dependent conditional probability without having a prior parametric model of anything. Suppose I have two variables: r and I, and each can ...
0
votes
0answers
11 views

Split a map into roughly equal sections directionally and put points in it

I have a 16000 x 9000 grid map and I want to split it into x sections that are preferably of equal size. Then I want to place points on each section are centers of circles with a 2200 unit radius and ...
0
votes
0answers
21 views

Is it better to average the log2 for a series of numbers or just the numbers themselves? And, how would you test or prove this?

Lets say I'm trying to compare two vectors for similarity and normalizing them before hand based on some mean or standard deviation combo for the purpose of finding the similarity between the 2 ...
0
votes
0answers
19 views

Neural Networks: Solving XOR

A perceptron with two inputs $x_1$ and $x_2$ has following linear function and is hence able to solve linear separateable problems such as AND and OR. $f((x_1w_1+b)+(x_2w_2+b))$ $f(x)$ is the basic ...
0
votes
0answers
104 views

What kind of graph is the StackExchange?

Assuming that we have three distinct layers of nodes called Users, Questions & Answers, connected by the obvious way $(A)$, what kind of graph is the StackExchange? Do such graphs have special ...
0
votes
0answers
23 views

Boosting v. weighted average

I have been watching an MIT online Artificial Intelligence lecture by Prof. Winston about boosting. The boosting technique uses complicated maths to combine the results from several weak predictors to ...
0
votes
0answers
9 views

How do I use resolution refutation in backward reasoning

Suppose I have the following facts in my KB: ∀a,b: g(a,b)→ p(a,b) ∀x: ¬p(x,x) ∀x,y,z: p(x,y)∧ p(y,z)→ p(x,z) ∀w,r: p(w,r)→ g(w,r) I have a questions: If I want ...
0
votes
0answers
30 views

hamiltonian graph problem (sitting problem)

Hello guys sorry for noob question but i am learning graph theory and i am solving a question . in book it says it have only four solution but i founded that it can more than four so i am confused . ...
0
votes
0answers
66 views

The mathematics behind Google Deepmind

I'm aware of the following question: The mathematics behind AlphaGo AI and Google Deepmind I'm aware of math behind Perceptron and several other AI concepts: ...
0
votes
0answers
26 views

Use of activation derivative in back propagation algorithm

I'm a little confused how the activation derivative in back propagation work. Firstly, when I remove the activation derivative from the back propagation algorithm and replace it with a constant the ...
0
votes
0answers
35 views

How to calculate probabilities in a Bayesian network?

Consider the Bayesian network represented by the directed acyclic graph given below: We are given the following probabilities: P(tampering) = 0.02 P(fire) = 0.01 P(alarm | fire ∧tampering) = 0.5 ...
0
votes
0answers
89 views

Solving differential equation using artificial intelligence

Hellow, I want to do my phd on the topics solving differential equation using artificial intelligence. At first I want to read some introductory books on artificial intelligence and then on the topic "...
0
votes
0answers
28 views

State space complexity of $2d$ and $3d$ tic tac toe

So for a 2d tic tac toe game, we know that the space complexity can be represented as follows. A naive upper bound will be $3^9$ as there is $3$ possibilities (X, Y or blank) in each of the $9$ ...
0
votes
0answers
14 views

Using differential evolution to evaluate weights

I have an equation I am attempting to optimise of the form: w1x1 + w2x2 + w3x3 Using a pre defined fitness function. Unlike any of the original papers, I also have the constraint: Sum of the ...
0
votes
0answers
22 views

How does Best First Search Calculate the Heuristic Values in the Graph

I understand that Best First Search uses a sorted open list based on Heuristic Values of the Nodes (priority queue) and a closed list.But how are these Heuristic values of the Nodes calculated? The ...
0
votes
0answers
15 views

What would linear neurons be able to model in artificial neural nets

Is it true that linear neurons are only useful in single layer neural nets because adding multiple layers will not allow the net to learn any interesting features because of the linear neurones?
0
votes
0answers
47 views

combine analysis and artificial intelligence

I'm sorry if I ask this question at the wrong place, but I don't know a better one. I am a Master's student and I am really interested in analysis, but I also want to get into AI. Does anyone know a ...