Questions tagged [ai.artificial-intel]

Theoretical questions about Artificial Intelligence

Filter by
Sorted by
Tagged with
0 votes
0 answers
21 views

Can the actions of one agent serve as the states of another agent in multiple-agent reinforcement learning (MARL)?

Imagine a piplelined process, where agent $A_1$ processes some information, and after that agent $A_2$ does some further processing based on the initial results of the first agent. The agents work in ...
  • 1
0 votes
0 answers
83 views

What are the capabilities of current Boolean Satisfiability Solvers?

I am wondering how well current Boolean Satisfiability solvers are able to perform — for example, are the best SATsolvers able to solve problems from SATlib?
1 vote
0 answers
52 views

sophistication or logical depth to detect intelligent extra-terrestrial species

From my understanding, Algorithmic information theory (AIT) gives some ways to define the amount of « structure » in a string: for example sophistication or logical depth (see for instance [1]), can ...
0 votes
0 answers
97 views

What's the relevant CS theory for CodinGame challenges?

CodinGame challenges are basically extremely large decision trees, where your program is trying to find the node with the highest possible score. Greedy algorithms don't work because picking a locally ...
  • 109
0 votes
0 answers
105 views

How much computer science / software experience is needed for a math major to do work in AI?

As a math major who is planning on getting their PhD in mathematics, how much computer science or software engineering experience/education do I need to comfortably do research in AI, i.e., would a ...
-1 votes
2 answers
186 views

Machine Learning Algorithm To Fill Data Holes

I'm having trouble finding a good place to begin with this. I'm just looking for a name or point to start researching a Let's say I have 1000 records. 10 of these records are only 90% complete. The ...
3 votes
0 answers
66 views

Are there experiments in artificial life on the emergence of sexual reproduction (analogues)?

I'm aware of quite a few experiments on the emergence of replicators in various artificial life areas, e.g. from cellular automata to computer programs. Have any similar result been obtained on the ...
  • 481
1 vote
0 answers
79 views

A question on the Kolmogorov Complexity of Human I/O behaviour

Note: From my Twitter poll I managed to get feedback from AI researchers and neuroscientists so far and I think it would be interesting to get input from theoretical computer scientists on this ...
2 votes
1 answer
110 views

Stochastic gradient methods and risk of neural nets

Under many situations it is currently provable that we can minimize the risk of neural nets using stochastic gradient based algorithms. For example : https://arxiv.org/abs/1811.03804, https://arxiv....
  • 1,443
1 vote
0 answers
109 views

Is this algorithm similar to any none in the literature?

I thought of the following algorithm for game AI, which is kind of a mashup of miniMax and Monte Carlo Tree Search. We assume that we have a heuristic function that assigns game states a value in the ...
  • 471
-4 votes
1 answer
152 views

Are there proofs which show that AIs are bound to be "worse" than the human brain? [closed]

I was talking with two PhDs (both teach IT related subjects) about artificial intelligence the other day. They were in agreement that an AI can never reach the level of the human brain, but failed to ...
1 vote
0 answers
236 views

Convergence of Q-learning with non-linear function approximation

Q-learning is a well-known algorithm in Reinforcement learning which enjoys great empirical success but with insufficient theoretical understanding. In the tabular setting, it is known that if each ...
  • 451
0 votes
1 answer
503 views

Serial and parallel neural network [closed]

The question is: can exist a parallel or serial neural network or someone talked about this? For explanation, in the network a single record in a data set enter in the input layer as a value between ...
  • 11
1 vote
1 answer
609 views

Minmax vs Maxmin

I'm reading this paper about building a combat simulator for 8 unit vs 8 unit mini combats in StarCraft: Brood War. The basic idea is to build a search tree simulating these small combats in order to ...
  • 113
-3 votes
1 answer
66 views

Is it correct to call systems with agents without BDI multi-agent systems? [closed]

The question concerns two fields - multiagent systems in AI and in software engineering. As the source of the term comes from the AI field, I ask the question here. Traditionally multiagent system (...
  • 93
16 votes
4 answers
735 views

Program reasoning about own source code

The inspiration for this question is the following (vague) question: What are the programming language/logical foundations for having an AI which could reason about its own source code and modify it? ...
0 votes
0 answers
221 views

Efficiently computing propagation values for only a few positions in a grid

Consider a matrix filled with some nodes containing positive integers ("starts"), some nodes marked as a wall, and the rest of the nodes given a value of infinity. The propogation rule is simple: For ...
  • 1,102
3 votes
2 answers
457 views

Representation of procedural knowledge

I know that knowledge about relationships between things can be represented using ontologies and stored in some sort of file or database system. Can a network of procedural knowledge also be created ...
5 votes
0 answers
197 views

Exploring a DFA, with no feedback

Let $M=(\Sigma,S,s_0,\delta)$ be an (unknown) deterministic finite-state automaton (DFA), with alphabet $\Sigma$, statespace $S$, start state $s_0 \in S$, and transition relation $\delta$. I want to ...
  • 10.5k
-3 votes
1 answer
561 views

Mapping input and output sequences using neural networks in high dimensional data

I have this huge dimensional data with 31200 features and only 6000 examples. I want to learn a neural network that can find the non linear relation between the input and outputs. However, I have ...
-4 votes
1 answer
205 views

What exactly is a search space? [closed]

I am new to CS so excuse my question if it seems very rudimentary. I just want to make sure I understand the terminology 100% correct as I go along. Is a "search space" the total amount of all the ...
3 votes
2 answers
229 views

AI strategies for losing positions

I have a card game that I am analyzing with Maple. Actually, it's a series of card games, one for every parameter k, where k is a natural number (representing the number of ranks of cards used in the ...
0 votes
3 answers
694 views

Algorithm Suggestion for Scoring System - weighted solution

I'm trying to validate a series of words that are provided by users. I'm trying to come up with a scoring system that will determine the likelihood that the series of words are indeed valid words. ...
8 votes
1 answer
386 views

Is $\mathsf{P} = \mathsf{NP}$ relative to a universal predictor?

Consider any language $L$. Define $s(L) \in {\lbrace 0, 1 \rbrace}^\omega$ (an infinite sequence of bits) by the recursive formula $$s(L)_n=\chi_L(s(L)_{<n})$$ Here $\chi_L$ is the characteristic ...
  • 2,161
-5 votes
1 answer
2k views

Developing A Perfect Tic-Tac-Toe Player - AI [closed]

I'm interested in AI as an area to study on in MSc. I don't have much prior knowledge. So, I decided to develop an AI that plays Tic-Tac-Toe perfectly, as an introduction. I've made some progress that ...
  • 1
0 votes
1 answer
109 views

When to apply soft constraints evaluation functions in genetic algorithms?

As stated in the question, say i created a random population of 100 timetables. 1 % of these timetables are valid. Then, if I apply the soft constraints evaluation functions on the 1% valid timetables,...
  • 1
-3 votes
1 answer
215 views

Can Turing Machine implements Strong AI? [closed]

It has been proved that a Turing Machine cannot solve the halting problem, but is it (being able to solve the halting problem) really necessary for implementing Strong AI ? We human can understand ...
  • 105
27 votes
5 answers
61k views

To what extent is "advanced mathematics" needed/useful in A.I. research?

I am currently studying mathematics. However, I don't think I want to become a professional mathematician in the future. I am thinking of applying my knowledge of mathematics to do research in ...
0 votes
1 answer
330 views

Self-organizing maps algorithm(Kohonen networks)

In self-organizing maps(SOM) algorithm described here it is said about the weights of nodes and data items. If using this algorithm for sine function approximation given a few points are the nodes - ...
  • 109
-3 votes
1 answer
226 views

Which algorithm for a project about online machine learning?

I have a basic understanding of how machine learning works, but my knowledge isn't enough in order to develop a personal project I would like to start. I want to develop a system based on online ...
2 votes
0 answers
762 views

Ultimate Jedi Challenge - Multiarmed Bandit / Reinforcment Learning / advanced AI problem

(This is an attempt to reformulate this question more concisely.) Context You are a Jedi master who wants to prepare a training program (online-algorithm) for his apprentice, "Luke". Luke needs to ...
  • 180
2 votes
3 answers
311 views

Complexity of universal computation on random input

This post is a refinement of a previous question which turned out to be trivial It is also related to another previous question Motivation: A property commonly ascribed to artificial intelligence is ...
  • 2,161
1 vote
1 answer
163 views

Average performance of universal computation

This post is related to my previous question but takes a different angle There are several related questions in here Consider an input-less algorithm $A$ generated randomly using a prefix-free ...
  • 2,161
12 votes
2 answers
604 views

Efficient universal problem solver?

Define a "problem" to be an algorithm $A$ accepting a natural number and returning 0 or 1 which returns $1$ on at least one $n \in \mathbb{N}$. Any such $n$ is called a "solution" to $A$ Define a "...
  • 2,161
0 votes
1 answer
145 views

Logic programming with integer or even floating point domains

I am reading a lot about logic programming - ASP (Answer Set Programming) is one example or this. They (logic programs) are usually in the form: [Program 1] Rule1: a <- a1, a2, ..., not am, am+1; ...
  • 409
2 votes
2 answers
578 views

Accuracy rate in neural networks

I've implemented a neural network (using the back-propagation algorithm) in a digital marketing application, where the algorithm classifies words according to quality, price and another ...
  • 29
1 vote
1 answer
563 views

Theoretical proof of convergence of sequential weight update procedure (Neural Networks and Machine Learning)

My question is at the bottom. (Most of the descriptive words come from Chris. Bishop's Neural Networks for Pattern Recognition) let $w$ be the weight vector of the neural network and $E$ the error ...
  • 105
-2 votes
1 answer
227 views

Error in the book Artificial Intellingence Modern Approach (at Un-informed search)? [closed]

Please let me know if this is not appropriate question to ask here (I hope not but afraid since this isn't really theoretical question). In the book "Artificial Intelligence Modern Approach" (Russell,...
  • 107
2 votes
0 answers
190 views

Computational power of cellular neural networks

A cellular neural network is a kind of recurrent neural network that could be thought of as a hybrid between neural nets and cellular automata. As I understand it, the classic Chua-Yang CNN is ...
  • 216
1 vote
1 answer
232 views

What is the most Accurate way of Determining an Object's Color? [closed]

I have written a computer program that can detect coins in a static image (.jpeg, .png, etc.) using some standard techniques for computer vision (Gaussian Blur, thresholding, Hough-Transform etc.). ...
1 vote
2 answers
4k views

What are some examples of sequential-decision tasks?

I ask this because I'm currently learning about Neural Networks as a subset of the machine learning algorithms Just trying to get some intuition on what sort of problems out there are categorized as "...
1 vote
0 answers
277 views

Are there any well known algorithms for synthetic handwriting?

Please excuse if this is too practical. I decided it was not technical enough for stack overflow and probably suitable for here. Given a set of letters, A-Z, what is the best scalable way to ...
5 votes
2 answers
2k views

Why is Bayesian filtering better than Neural Networks when classifying spam?

According to several people on StackOverflow Bayesian filtering is better than Neural Networks for detecting spam. According to the literature I've read that shouldn't be the case. Please explain!
  • 175
-6 votes
1 answer
220 views

AI or not an AI [closed]

What truely classifies a AI? IN science fiction they are thes super smart programs that usually try taking over the world. In the programming world i hear about AI for enemies in games or stuff along ...
  • 101
0 votes
0 answers
298 views

Fuzzy K-modes clustering how to find the cluster centers

I'm trying to understand [fuzzy k-modes][1] algorithm (look mainly at page 3) in order to implement it. I'm stuck at the calculation of cluster centers they said as shown in the link https://...
  • 101
0 votes
3 answers
480 views

Formalizing a notion of machine Intelligence

Turing test of Artificial intelligence relies on interaction between two parties with the goal that one party convinces the other party that it has the same computational abilities. I'm trying to ...
5 votes
4 answers
1k views

Genetic Algorithm to Draw a Graph? Position assignment problem

I have an assignment problem at hand and am wondering how suitable it would be to apply local search techniques to reach a desirable solution (the search space is quite large). I have a directed ...
  • 153
1 vote
0 answers
59 views

What Fuzzy techniques can combine conflicting quantified data?

I have been reading Fuzzy Belief Revision and trying to determine how the methods could be used to combine readings from conflicting sensors. For example, if one sensor reads 70 degrees and another ...
4 votes
1 answer
127 views

Are there Belief Revision techniques for quantified data?

Are there Belief Revision techniques that aren't based solely in formal logic propositions? For example, if one agent believes the temperature for an area is 85 degrees and another believes the ...
3 votes
2 answers
361 views

Support Vector Machines

What is it the relationship between the number of support vectors in an SVM and its generalization ability? When lots of support vectors are used to classify, is the error rate minimized, but only to ...
  • 131