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

learn more… | top users | synonyms

5
votes
1answer
19 views

The meaning of discount factor on reinforcement learning

After reading of the google deepmind achievements on Atari's games, I am trying to understand the q-learning and q-networks, but I am little bit confused. The confusion arise in the concept of the ...
0
votes
0answers
16 views

Introduction to Artificial Intelligence [on hold]

I adore artificial intelligence and all of its applications. However, I have a very basic and theoretical knowledge of it. I'm looking to get more well versed and even start working on complex ...
0
votes
0answers
30 views

Is forward chaining space friendlier compared to backward chaining?

In the context of rule-based systems, is forward chaining more efficient than backward chaining? I know that forward chaining is used when we know some facts and from there we want to conclude some ...
0
votes
1answer
23 views

Heuristic function

Is there any way to prove that an admissible heuristic may not be consistent? Most proof I came across are through examples .Is there a generalized proof?
1
vote
0answers
46 views

How to select the maximum weight value for a bias node in a neural network?

I'm programming a neural network. I know that I should initialize the network by picking random weights. How do I pick a random weight for the connections to bias nodes? What distribution should I ...
3
votes
0answers
31 views

Alpha beta algorithm with Iterative Deepening analysis

I'm implementing a chess engine. Like many engines, the search for the next best move is done with the alpha-beta algorithm. There are many improvements that can be made to make the algorithm faster ...
1
vote
2answers
78 views

Machine learning algorithm(s) for recognizing simple graph patterns

I generate some simple graphs based on usage stats of a website, and they may look like these: I call the 'pattern' on the left 'convergence', and the 'pattern' on the right 'divergence'. The ...
7
votes
1answer
54 views

Is there any published paper about automated planning software used in the ESA Rosetta mission?

The Rosetta spacecraft has reached a comet in August 2014 and sent a lander on its surface. It was one of the greatest science news of the year. Automated Planning and Scheduling techniques are ...
0
votes
0answers
23 views

Lattice of a fuzzy number?

Can somebody define what is a fuzzy lattice? How to compute 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 ...
3
votes
1answer
61 views

the meaning of heuristics in artificial intelligence

I would like to know what 'heuristics' actually means in artificial intelligence. For example, I am reading a paper by Engelbrecht on the convergence analysis of the particles of the algorithm. The ...
1
vote
0answers
45 views

Is it even theoretically possible to invent coumputers that are more intelligent than humans? [closed]

I've read an article recently where Stephen Hawking claims that in hundred years there will be computers, which are more intelligent than humans. Link: ...
1
vote
1answer
60 views

Perceptron learning rule past exam question

I'm struggling to solve this past paper question and my lecturer is being less than helpful. The question is: Apply the perceptron learning rule to update the current weight vector (0.1, 0.3) when ...
0
votes
0answers
68 views

How to apply Alpha-Beta pruning to a game tree? (Algorithms Theory)

I'm studying for an AI exam, and having trouble working out this question on Alpha Beta pruning. I can answer on the effectiveness of the pruning method and the rules involved in the pruning process, ...
3
votes
1answer
62 views

What is the name of this problem in Computer Vision?

My google skills have failed me during research for a college project. Our task is write a program that describes an image in spacial terms, e.g. "Cat on the left of a chair", or for a simple image ...
1
vote
1answer
52 views

Standard problem sets for metaheuristics

I'm wanting to dabble with metaheuristics and am interested to know what the "hello world" problem sets are. In other words, what are the common problems (e.g Traveling Salesman, Vehicle Routing ...
2
votes
2answers
52 views

Why can Multilayer neural networks solve non-linear problems

I understand what a multilayer neural network is, but what about them allows them to solve non-linear problems unlike perceptrons? Is it the fact that they can extend to any number of outputs/hidden ...
1
vote
0answers
12 views

How to determine convergence when using Q-learning?

I'm using Q-Learning to find the values of states in on a gameboard. For example, something like: ...
1
vote
0answers
15 views

Adversarial Monte Carlo Tree Search Assymetry

Monte Carlo Tree Search with UCT is praised for it's assymetric tree growth, growing promising subtrees more than non-promising ones. But in a 2-player adversarial game, when a win at one node is a ...
1
vote
1answer
29 views

Is it possible to create a human thinking and acting program on a computer? [closed]

Does Artifical Intelligence need something else, something that is not so limited as a computer to achieve the goal of building a humanly thinking and acting program? If so, what might this be? I ...
1
vote
1answer
48 views

Differences between linear/nonlinear vs. deterministic/nondeterministic neural nets

When speaking of neural networks, I don't get the difference between nonlinear and non-deterministic. Basically, both say that the output of something is not directly correlated to the input? Hope ...
-1
votes
0answers
51 views

Could there be an end of (human-organized) databases? [closed]

I'm not a computer science guy but just curious about a potential decline of databases. I believe there will always be data, that's for sure, but would there always be databases? Databases are a ...
0
votes
0answers
24 views

Numerical Boardgame — Help with with a pruning method (alpha-beta : minimax)

I'm developing a simple AI to play a boardgame which consists of N x N squares, each with a predefined value. ...
0
votes
1answer
42 views

What is a sufficiently complex system?

I have been reading about the AI approaches, and I came across the AI emergent approach that has the following definition: That is, the appearance of an entity with a sense of its own identity and ...
1
vote
1answer
208 views

Why can't we solve the Halting Problem by using Artificial Intelligence? [duplicate]

Yesterday I was reading about Computability and they mention the Halting Problem. It got stuck in mind all day until I remember that some weeks ago, when learning Java, the IDE (Netbeans) show me a ...
0
votes
1answer
39 views

Updating connections weights in neural networks

I am learning about neural networks and have a couple of things I don't understand. Firstly, in competitive learning I understand that only the neuron with the strongest output is reinforced. That is ...
0
votes
0answers
105 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 ...
1
vote
0answers
23 views

Research work on computational models for a “specific” person's behaviors

Is there active research work on creating computational models of a "specific" person's behaviors (general behaviors, emotions, actions...)? What are some references for such research? I tried google ...
14
votes
4answers
4k views

Did 'Eugene Goostman' really pass the Turing test?

It is being said that 'Eugene Goostman', a computer programme developed to simulate a 13-year-old boy, managed to convince 33 per cent of the judges that it was human, and thus passed the Turing Test. ...
0
votes
0answers
15 views

Previous approaches for encoding physical affordances

From Wikipedia, an affordance is: a relation between an object or an environment and an organism, that affords the opportunity for that organism to perform an action Previously what approaches ...
0
votes
1answer
43 views

What is a continuous environment for an agent?

I know the environment of an intelligent agent is divided to discrete and continuous. But I think they are relevant to sensors and actuators of the agent itself. Moreover, environment may have many ...
0
votes
2answers
57 views

Which type of computer programs could be called intelligent agents?

I know some computer programs can be modeled as intelligent agents, for example a chess program which plays against a human. The environment is the chess board stored in the memory and actuators are ...
0
votes
0answers
22 views

Can Ontologies be used for defining tactics and technical features?

The generic use of ontologies is defining terms and relations between them in a specific domain. And in some cases they are used with the cognitive architectures to make intelligent agents for ...
4
votes
4answers
302 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 ...
3
votes
1answer
121 views

Who coined the term “artificial intelligence”?

The most obvious (and commonly given) answer to this question is John McCarthy, but I have traced the first usage of this term to a 1955 paper, which McCarthy co-authored with Marvin Minsky, Nathaniel ...
1
vote
0answers
47 views

Formulating an arrangement problem with STRIPS

The problem is rearranging furniture in a flat. We are given rectangular rooms of natural width and height with doors between them, (the walls have no width) and rectangular furniture at starting ...
1
vote
1answer
461 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? Thank you~
1
vote
0answers
169 views

What is an example of Licklider’s idea of man-machine symbiosis in constructing information systems?

I am trying to understand Licklider’s idea of man-machine symbiosis in the real world, does anyone know of any real world examples of the use of a man-machine symbiosis? Would it be correct to say ...
-1
votes
1answer
92 views

Books to get prepared before self studying Artificial Intelligence [closed]

I want to study Artificial Intelligence from Artificial Intelligence: A Modern Approach by Russell and Norvig, in the mid-year vacation. I want to get prepared before diving into the book so I decided ...
1
vote
1answer
72 views

negative effective branching factor it's possible?

i've implemented A* algorithm in python,after that i calculate with this python function the effective branching factor $ B^* $ $ T+1=1+B^*+(B^*)^2+⋯+(B^*)^L$ where $T$ is the number of expanded ...
0
votes
1answer
48 views

Why do heuristic functions only approximate the real value of the cost?

As stated in the title I'm wondering why do heuristic functions only approximate the real value of the cost? I understand it can never overestimate, but can it ensure the cost is accurate?
2
votes
3answers
131 views

Can someone clarify this unification algorithm?

I've been having trouble understanding a unification algorithm for first order logic, as I don't know what a compound expression is. I googled it, but found nothing relevant. I also don't know what a ...
4
votes
1answer
286 views

Genetic Algorithm, Neural Network, Deep Learning, Machine Learning Similarities and Applications? [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
2answers
309 views

ANN - Backpropagation with multiple output neurons

Can I utilize the backpropagation algorithm in a layered, feed-forward ANN in instances where there are multiple output neurons? If so, how? Links to (somewhat) comprehensible resources would be ...
0
votes
1answer
36 views

what is the general name of this problem?

what is the general name of a problems where learning agent observe new data as a learning goes on. For example when playing platformer games one must incrementally learn new level areas and states ...
1
vote
1answer
40 views

Programs for artificial system design? [closed]

Are there program systems that can discover the need of routines - and then design them, code them and use them as parts of the system? Any group of humans trying to pursue an activity has to ...
1
vote
0answers
42 views

Formula for number of parameters in an undirected graphical (probability) model

I have googled endlessly, and I cannot find it. Can anyone point me to a reference that gives a way to calculate the number of parameters in an undirected Graphical Model? Adapting from the similar ...
0
votes
2answers
93 views

Why is And-Or-Graph-Search called a search algorithm?

An algorithm in Artificial Intelligence: A Modern Approach for planning in stochastic, fully observable environments is called And-Or-Graph-Search, implying that it's a search algorithm. However, I ...
3
votes
0answers
81 views

Prerequisites for AI and machine learning [closed]

I am interested in the field of AI and machine learning and I am fairly good at mathematics and statistics and programming in general. However I lack a formal CS education and my undergraduate degree ...
0
votes
1answer
118 views

Forward checking with conflict directed backjumping [closed]

Can somebody explain me how can I join forward checking with conflict directed backjumping in my CSP solver? I understand that when the consistency fails when I add a value to a variable, I should ...
0
votes
0answers
9 views

Hierarchical reinforcement learning exploration methods

One of the extensions to hierarchical reinforcement learning is change the degree of randomness that is applied while choosing an action. It is possible to increase the randomness to encourage ...