Questions tagged [artificial-intelligence]

Questions about design and properties of agents that act in a dynamic environment and make decisions towards some goal without user control.

Filter by
Sorted by
Tagged with
1
vote
1answer
41 views

“Learning occupancy grid maps with forward sensor models, S.Thurn,2008” a formula that is difficult to overcome

I am reviewing the document" Learning occupancy grid maps with forward sensor models, S.Thrun, 2008" (http://faculty.iiit.ac.in/~mkrishna/ThrunOccGrid.pdf) i am really confused about formula (26), ...
1
vote
1answer
350 views

what's analogy learning algorithm ? differences from induction learning algorithm? [closed]

I am a computer engineering student and trying to get the idea behind all these Artificial Intelligence Concepts and applications. I know little theoretically about machine learning and some high ...
2
votes
0answers
277 views

The meaning of ontology in computer science

I am reading a paper and ran into this word Ontology-based, What does it really mean? I did searching about it but still ambiguous to me, can someone elaborate this ...
2
votes
1answer
31 views

how to approximate a very complex optimal policy when the distance function is unknown

A policy $P$ is defined as a set of parameters. We want to know the optimal policy $O$, which certainly exists but unfortunately unknown. $D(P)$ shows how far $P$ is from $O$. The function $D$ itself ...
1
vote
0answers
170 views

Any reason to use the least-constrained variable heuristic when searching the solution of a CSP?

Is there any (kind of) (well-known) problem which can be expressed as a CSP in which the least constrained variable heuristic seems to give the best results, when employing backtracking with ...
1
vote
1answer
903 views

Representation of 8-Puzzle for (A*) Search Algorithm in C

I am trying to complete CS50's hacker edition pset3, where you have to make a program that will solve the game of eight or fifteen from its current state, this must be written in C. https://en....
0
votes
1answer
2k views

What is Turing's main argument in “Computing Machinery and Intelligence”?

I read Alan Turing's paper "Computing Machinery and Intelligence" a few times and it isn't clear what exactly is he arguing for. He proposes the imitation game, but doesn't form a concrete conclusion. ...
1
vote
1answer
1k views

Heuristics for the $n$-puzzle

An admissible heuristic for an n-puzzle is the Manhattan distance. Now if the cost of a transition is equal to the number of the piece that is moved, is it true that the Manhattan distance is still an ...
3
votes
0answers
146 views

Is “expert system” now an obsolete/unpopular term?

While doing research on expert systems, I notice that it is rare to see this term used in the last 20 years. For example, a recent paper was: Wang, Hao, Naiyan Wang, and Dit-Yan Yeung. "Collaborative ...
1
vote
1answer
672 views

how can i know if a First order logic sentences is valid or unsatisfiable or neither?

i have trouble with understand this type of questions , i know how i can determine if the sentences is valid or unsatisfiable in Propositional logic , but in FOL i can't for example , i have the ...
1
vote
2answers
1k views

Using tree search

I have some questions regarding tree search and graph search (Uninformed search) as explained in chapter 3 of the book : http://aima.cs.berkeley.edu/ As I see, the only difference between the two is ...
1
vote
0answers
188 views

Qualification or Disqualification of Machine Intelligence test as “Turing test”?

Let's us the following definition: Tu·ring test noun A test for intelligence in a computer, requiring that a human being should be unable to distinguish the machine from another human being by ...
0
votes
0answers
124 views

Let me know about ANFIS premise prameters

I wanna ask about Adaptive Neuro Fuzzy Inference System (ANFIS) method. I used clustering to find fuzzy rules and used the mean and deviation standard of each cluster for initialization of the first ...
2
votes
1answer
305 views

Convergence of Markov model

I was learning Hidden Markov model, and encountered this theory about convergence of Markov model. For example, consider a weather model, where on a first-day probability of weather being sunny was 0....
4
votes
1answer
120 views

Any significance to why a lot of big names in AI have math PhD?

I've been looking into AI research and I've noticed a nontrivial amount of individuals either received a PhD in math or had advisors who received a PhD in math. Some names include (Ben Goertzel, ...
5
votes
3answers
341 views

Are the Confabulation Theories of Thaler and Hecht-Nielsen Isomorphic?

Both S. L. Thaler and R. Hecht-Nielsen have set forth neural-based theories of "confabulation" applicable to machine learning. The essential mathematics of Hecht-Nielsen is set forth in his paper "...
1
vote
0answers
46 views

Modify g(n) and f(n) in A* Search

I know that the formula for the evaluation function in A* Search is given by: $f(n)=g(n)+h(n)$ I was wondering what would happen if I made h(n) negative. I suppose it doesn't make sense to have path ...
2
votes
1answer
46 views

How to model a set of categorical values in the input of a neural network

One of the inputs to my neural network is a set. I have a set $S = \{s_0, s_1, ..., s_n\}$ in which all values $s_i$ are constant. An example of such a set could be the set of French wines (...
3
votes
1answer
55 views

How can image processing neural networks be effectively trained?

I was just thinking about image processing neural networks and how to effectively train them in regard of the available dataset. Let's say you'd want to build a neural network which can distinguish ...
3
votes
1answer
642 views

Can you solve 3D Tic Tac Toe with Minimax?

I have implemented a 3d Tic Tac Toe game with AI, where the computer is unbeatable. The only thing is that the board looks like this: _ _ _ _ _ _ _ _ rather ...
0
votes
1answer
2k views

Prove consistency of maximum of two consistent heuristic functions?

Suppose we have two heuristic functions $h_1$ and $h_2$ which are both consistent, that is, $$h_i(n) \leq c(n,a,n') + h_i(n')\qquad \ i\in\{1,2\}\,,$$ where $c(n,a,n')$ denotes cost of reaching the ...
1
vote
0answers
925 views

How can I integrate an android app with expert systems using SWI-Prolog? [closed]

I want to build an expert system that runs on android. I am using Android Studio as my development tools and I already started to build the knowledge base using SWI-Prolog. I want to take the result ...
3
votes
0answers
134 views

A case study for search techniques in AI

We are teaching an artificial intelligence class and we need a different case study other than geographical maps (the popular example is the map of Romania) to explain the difference between Breadth-...
0
votes
0answers
71 views

API to retrieve answers for general questions

I was looking for a service (with API) where I can ask it a general question (aka, when was Einstein born?) and retrieve an answer from the Web. Is there any available service to do that? Have tried ...
3
votes
0answers
24 views

proof that STRIPS terminates

I was reading page 6 of https://www.cs.cmu.edu/~reids/planning/handouts/Linear.pdf And it is not clear to me that the STRIPS algorithm necessarily terminates. Namely if we have a simple goal sg on ...
8
votes
5answers
3k views

What are the practical uses of ontologies?

I have read many papers and books about ontologies and I am trying to figure out that how they are used in a real project? For example how the ontology for a soccer player robot can be defined and ...
0
votes
1answer
525 views

Does expert system use algorithms? [closed]

I want to build an expert system for analyzing the personality of a number of people and then distribute them in groups , each group will have members with different personalities. I have been ...
0
votes
1answer
381 views

Using AI / Machine learning to find the most time and space efficient solutions to an algorithm [duplicate]

As programmers, we are always trying to find the most efficient space and time complexity solutions to algorithms. Is it forseeable in the future that we have languages or techniques such as AI/...
-2
votes
1answer
79 views

Is a Neural Network's weight selection dependent on its architecture? [closed]

Would an optimum combination of weights for a given topology necessarily be the the optimum for a different topology ?
3
votes
1answer
94 views

Confusion regarding terminology surrounding perceptron learning

I am having trouble understanding the terminology with perceptron learning. Is my current understanding correct? Let's say I have some data that classifies what type of flower a particular flower is. ...
4
votes
2answers
1k views

How can I compare two different neural networks, from a theorical point of view?

Let's say I have a problem (i.e. Given f(x), find x) and two neural networks(i.e. feedforward and recurrent). I would like to know if one works better than the other one. I could run the twos on a ...
0
votes
1answer
67 views

Is it possible to get information from websites as a human? [closed]

If I want to read any websites and get some information as names (or dates) on some part of the site as a human. What solution I could use in order to get these datas using deep learning or machine ...
0
votes
0answers
77 views

What is the state-of-art ML techniques for the problem of writing algorithms?

Could any existing ML technique be used, for example, to solve the problem of building a lazy Sieve of Eratosthenes in Haskell? By that, I mean a program that, given a specification (a dependent type ...
3
votes
0answers
1k views

Estimating size of state space

I have been studying search problems in AI, and I am having some troubles understanding some points in these concepts: State Space: "represents the environment of the problem, the set of all states ...
0
votes
0answers
228 views

Support Vector Machines vs K-Nearest Neighbors

Let's say we have trained a Support Vector Machine with a Gaussian Kernel. When we feed our model an example, it classifies it based on its similarity to landmarks (distance to examples in our ...
3
votes
0answers
77 views

Is there a reduction concept in artitificial intelligence?

Is there a concept for comparing algorithms in artificial intelligence theory similar to reduction in complexity theory (Wikipedia)? I'm asking this because I was wondering how AI algorithms are to ...
4
votes
1answer
357 views

How do neural networks create results like its inputs?

I understand basic neural networks (input layer, hidden layers, output layer) and gradient descent learning. However I keep hearing about news talking about neural networks painting and making jazz ...
2
votes
1answer
511 views

decidability of artificial intelligence

Not sure whether this is the correct place to post the question. some of my terms might not accurate. currently AI is used for classification, inference, and so forth, is AI problem decidable? for ...
1
vote
1answer
1k views

How come the branching factor of chess is 35?

I was studying about minmax algorithms and it said the branching factor of a chess game is around average 35. Meaning a player can move about 35 legal moves per position. I am not able to comprehend ...
0
votes
0answers
124 views

Halting problem and simulation of intelligence [duplicate]

According to halting problem, there is no algorithm which can decide if another algorithm and its input will halt or not. Suppose human intelligence can be simulated in a computer. Also suppose than ...
2
votes
0answers
103 views

Problem understanding Nilsson's general graph search and A* algorithm

I'm reading several books that present A* algorithm. More precisely, I'm Nilsson's "Artificial Intelligence a New Synthesis" and a textbook on problems of artificial intelligence which is written in ...
0
votes
2answers
916 views

Best starter resources for learning about AI [closed]

I want to start learning of AI and have an idea to program "social evolution simulator" but want to hear any advice to avoid creation "well known bicycles" and get strong knowledge-base. Will be ...
3
votes
1answer
224 views

What method of collective recogintion to use for digits recognition?

The structure of the question is as follows: at first, I provide the concept of collective recognition, further I provide explanation of the various methods of group classification that I found, in ...
1
vote
1answer
2k views

Iterative lengthening search: iterative version of Uniform Cost Search or DFS?

Actually my question has two parts: 1) I wanted to know that whether Iterative Lengthening Search is used in combination with DFS or Uniform Cost Search? Actually, in Russell and Norvig book (on page ...
3
votes
2answers
81 views

Genetic Algorithms: Converge to best solution for one, few or many environments?

Let's say we take someone's garden (A) as the environment. We want a robot to pick up a series of eggs that chickens have laid in the garden, while covering as little ground as possible (those heavy ...
3
votes
1answer
12k views

Cognitive Computing vs Artificial Intelligence?

Can anyone please tell me the difference between them? A brief definition of Cognitive Computing would appreciated. Also how does cognitive computing relate to neural networks?
0
votes
0answers
34 views

How would physical neural nets learn?

I understand how neural networks that are implemented in software learn. You simply change the synaptic weights in the program. But how would you get a hardware implementation of neural networks to ...
0
votes
0answers
32 views

Something wrong when recognizing data set using Binary Artificial Neural Network

I have learnt Neural Network for a couple weeks. I just met a problem when I tried to use ANN to recognize a dataset. So I'm gonna describe the problem: Set A has 15 members which are in set {1, 1.5, ...
-1
votes
2answers
924 views

Perceptron learning rule for classification

That's the problem $$y=(x,w,\rho) = \begin{cases} 1 & \sum_{i=1}^3 w_ix_i >\rho\\ 0 & \text{otherwise} \end{cases},$$ where $x=\{x_1,x_2,x_3\}$ are inputs, $w=\{w_1,w_2,w_3\}$ are ...
0
votes
0answers
374 views

Compute connect-four opening moves

my question is about how to compute a database with initial moves for Connect Four, where each board constellation is classified as leading to a win, draw or lose. John Tromp already has done this ...

1
3 4
5
6 7
10