For questions about artificial intelligence.

learn more… | top users | synonyms

0
votes
0answers
15 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 ...
2
votes
0answers
17 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 ...
1
vote
1answer
43 views

LOGIC - Completeness vs Consistent

One of my exams questions were the following (translated from Hebrew) Course is in Artificial Intelligence, and is about Logic in this question. What is a consistent logic system? What is a ...
1
vote
2answers
79 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 ...
0
votes
1answer
25 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. ...
1
vote
0answers
19 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
31 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
12 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 ...
0
votes
0answers
54 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
21 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
30 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, ...
1
vote
0answers
33 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 ...
0
votes
1answer
86 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
0answers
25 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 ...
0
votes
0answers
11 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
16 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
3answers
161 views

Reducing TIC-TAC TOE State Space by using Symmetry in Artificial Intelligence

Im learning Heuristics in AI.I see that for brute force search there are 9! states.But the textbook says that first 3 levels are reduced by symmetry.How does that work?
0
votes
0answers
13 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?
-1
votes
1answer
105 views

Math replacing natural language [closed]

Before reading any further. I ask yous to think creatively on this subject. I was in shower and was pondering over A.I. (Strong A.I. both at human level and beyond human level) as I do from time to ...
0
votes
0answers
35 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 ...
1
vote
1answer
61 views

Can you give a simple CDCL example?

I am trying to understand how Conflict-Driven Clause Learning works. After reading through the lecture slides, wikipedia article and some additional slides I found online I realized that I still can't ...
0
votes
0answers
25 views

Lattice of a Fuzzy Number?

Can somebody define what is a fuzzy lattice? How to computer lattice of a fuzzy number? Please try to be generic and basic in the explanation as I'm a beginner in studying fuzzy theory and soft ...
0
votes
1answer
39 views

Calculating Entropy

Hi there kind people, I'm studying for an Artificial Intelligence test in a week or so, and this question is from a past paper - and it has really stumped me. Any help would be appreciated. Thank ...
2
votes
0answers
82 views

How does Godel Escher Bach support Artificial Intelligence? [closed]

Typically, Godel's Incompleteness theorems have been used to argue against the possibility that the human mind is essentially equivalent to a formal system. However, in Daniel Dennett's book "Darwin's ...
0
votes
0answers
15 views

Applying a Resolution to a Predicate with Substiutions

My professor handed us an exam review with the answers already filled in. On this one particular problem I have no idea how he came to the answers he did. Question: Apply a resolution to the ...
2
votes
1answer
45 views

Finding the best fit of 3 categories ( restaurants/meal/person analogy problem )

I have this problem that sounds tedious and long and I'm not sure if there exist an intuitive way to solve it. The problem is related to image recognition but I will try to give an analogy to it You ...
0
votes
1answer
53 views

What does the notation ab1, ab2, etc. refer to in predicate logic?

I'm trying to decipher a set of relations from a John McCarthy paper: $$ specializes(c1,c2) \land \neg ab1(p,c1,c2) \land ist(c1,p) \supset ist(c2,p) $$ and $$ specializes(c1,c2) \land \neg ...
3
votes
2answers
55 views

Find sectors in a racing line.

Consider the following photo: To magnify image, right click and select open-image in new tab or something similar The photo above is a random race circuit data I've collected. What I'm trying to ...
0
votes
1answer
45 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
100 views

“Anything anyone eats and is not killed as a result is food” - First order logic representation

Given the required predicates: eats(x,y) : x eats y food(x) : x is food killed(x) : x is killed I am confused as to how to represent this statement in First Order Logic Would it be ...
2
votes
1answer
708 views

How to calculate Full joint probability distribution

This is a past exam question, I did it wrong in the exam, I'm reviewing it right now. The question is to compute the full joint probability of the problem below: I draw the full joint ...
4
votes
2answers
87 views

Are there some functions that cannot be optimized using calculus?

I've been working on a project to maximize a functions output using a genetic algorithm. However, from the limited calculus I know I thought there were methods to find the maximum of a mathematical ...
1
vote
0answers
45 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 ...
0
votes
1answer
37 views

Ellipsoidal Covariance Matrix

What does it mean when you say "Covariance matrix are highly ellipsoidal"? I am reading a paper and it uses this term very often "Covariance matrices are all equal and Highly ellipsoidal "?
2
votes
1answer
939 views

What is the sigmoid *squashing* function?

I've just read the following The basic unit ("neuron" i) performs the following computation to update its state $y_i$: it computes a weighted sum $v_i$ of its inputs $x:j$ which is passed ...
8
votes
3answers
1k views

What Maths are the most important for Artificial Intelligence?

I am just curious about this. Please don't include anything about programming.
1
vote
0answers
64 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
285 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 ...
10
votes
4answers
463 views

Application of computers in higher mathematics

Currently the main application of computers in mathematics seems to be to compute things, i.e. to solve equations, evaluate integrals, etc. It is at all possible to delegate the thinking of a ...
1
vote
5answers
405 views

First Order Logic

Is it possible to represent the english sentence with numerical value in First order Logic. For example if the sentence is: Nobody has more than one mother. I am wandering who can i show the ...
2
votes
1answer
223 views

Testing critical points using newton-raphson method

I'm working on a homework assignment for my artificial intelligence course and I became a bit stuck on one part. The problem asks to retrieve the optima of the function and then to tell for each ...
1
vote
1answer
1k views

Proving that a Hessian Matrix is positive definite

I'm currently stuck on a problem for my Artificial Intelligence class. The assignment is provided at the following link: http://courses.engr.illinois.edu/cs440/HW1.pdf The problems that I'm stuck on ...
2
votes
1answer
38 views

Markov Decision Process - Optimal policy invariance to scaling in the Utility Function

The title says it all. If i use a discounted Utility Function, why is the optimal policy invariant with respect tot the scaling of the Utility Function by a positive Factor?
0
votes
2answers
54 views

Why this first-order logic formula is not correct?

I'm studing computer science at university, in specific Artificial Intelligence. We are using Otter as Theorem prover. I'm having some problems formalizing this: "John, Mary and Derek are three ...
8
votes
1answer
1k views

Applications of Differential Geometry in Artificial Intelligence

I am new to this wonderful site. I searched around a bit but I couldn't find any well-discussed posts on applications of differential geometry to artificial intelligence, or more generally to computer ...
1
vote
1answer
1k views

Using implication with the Universal quantifier

While reviewing my AI textbook, I came across a paragraph that baffled me. It attempts to explain why the truth table for implication turns out to be perfect, as ...
4
votes
1answer
889 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*} ...
0
votes
1answer
179 views

Is a traditional Multi Layer Perceptron Network capable of non-linear regression? Which activation function should be used for that purpose?

I need to use a Multi Layer Perceptron Network in order to perform some non-linear regression. Any ideas if it's possible to perform a task like that and how? Which activation function should be used ...
0
votes
1answer
45 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 ...
1
vote
1answer
83 views

CHeck my proof of how I arrived at my answer

Show proof for: (P --> Q), P ^ (~ ~R & ~ ~ Q), (S --> ~ R), ~(P & Q) : (~S ^ ~Q) is this correct? (P --> Q) Premise P ^ ( ~ ~R & ~ ~Q) Premise (S --> ~R) ...