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

0
votes
0answers
6 views

Hierarchical learning in a non-static environment

I've been reading about hierarchical reinforcement learning (HRL), in particular it's application to a simple delivery task as show here. While reading the paper, I noticed that the environment ...
0
votes
0answers
8 views

Has hierarchical learning been embodied in a robot before?

I've been reading about hierarchical reinforcement learning (HRL) and it's applications. A well-written literature review on the subject can be found here. However, I was wondering if research has ...
-2
votes
0answers
29 views

What language for AI programming? [on hold]

What language should I use for AI programming? Python or C++?
2
votes
1answer
56 views

Is there a program that will tell you the optimal algorithm for ANY problem if the problem is decidable? [duplicate]

Is there a program that will tell you the optimal algorithm for ANY problem if the problem is decidable? If not, why not? If yes, how can such a program be realistically constructed? I would prefer ...
4
votes
3answers
120 views

Difference between weak and strong AI

I'm trying to understand the difference between weak and strong AI. For an example, let's say we would pass the turing test - would it show strong AI or weak AI then? I don't believe that this is ...
-4
votes
0answers
38 views

How can I compute the joint distribution of this Bayesian network? [on hold]

We have a Bayesian Network that A to D is Boolean variable. we want to calculate the probability which C and D be True and A be false. my answer sheet calculate the last result and is 0.0424. any ...
-1
votes
1answer
39 views

Automatically generate meaningful queries for a data table

My field of research is not Database or AI. But I have some problems to solve, and would like to know which branch this kind of problems belong to, and what are the results. The main question is: ...
2
votes
2answers
44 views

Is it possible to implement a Neural Network using a graph data structure?

I'm trying to implement a feedforward neural network using a graph. The thing is: I haven't found any example in which is used a graph data structure. So far the examples I've found used arrays. Can ...
1
vote
1answer
42 views

Generating hard puzzles for a backtracking snake

Let $M$ be a matrix of height $h$ and width $w$. Each entry of $M$ is an integer. There is a snake that starts from the "left side" of $M$, and its goal is to reach the "right side" of $M$. To get ...
0
votes
0answers
47 views

Activity prediction in a kitchen

Here is the scenario: There are three chefs(A- main chef, B and C- assistant) working together to prepare a diner set. The sequence of the event is as following. Start: The three chefs enter the ...
1
vote
1answer
39 views

Are neural networks dynamical systems?

Dynamical systems are those whose evolution can be described by a rule, evolves with time and is deterministic. In this context can I say that Neural networks have a rule of evolution which is the ...
2
votes
1answer
30 views

Closed form solution for a single layer linear perceptron

Let f be a one-layer neural network which is linear (ie. no activation function). Let it have $p$ inputs and $q$ outputs. These are fully connected by weights $W$. We have $n$ inputs $x \in ...
1
vote
1answer
43 views

What are practical applications of AI Planning? [closed]

note: any tips toward making this more constructive will be highly appreciated. I've dealt with ai-related problems, from searching algorithms, to computer vision, to machine learning. However none ...
1
vote
0answers
26 views

Understanding Decision Stump in Adaboost

I am trying to understand how Adaboost works, and many of the tutorials online involve the use of a decision tree stump. For example, http://www.cc.gatech.edu/~thad/6601-gradAI-fall2013/boosting.pdf ...
2
votes
1answer
32 views

Why does ε-greedy $Q$-learning not oscillate?

I have a intuitive question on the convergence of $Q$- learning. In $Q$ learning for each step a $Q$- value is learned for the state-action pair where the action is selected according to the ...
1
vote
0answers
24 views

What is the difference between “objective function”, “error function”, “criterion function” and “cost function” in the context of neural networks?

The title says it all: I have seen three functions so far, that seem to be the same / similar: error function criterion function cost function objective function I am currently working on ...
-1
votes
1answer
14 views

Training Error & Convergence to True Error

I Take some online class for Machine Learning. one of teacher say this sentence. if we have m data points, the training error converges to the true error as m → ∞. i thought, this sentence not ...
0
votes
1answer
28 views

VC Dimension Calculation for Intervals

As i See in ML Course a VC dimension calculation is very theoretical. What is the VC-dimension of intervals in R? The target function is specifieed by an interval, and labels any example positive ...
1
vote
3answers
144 views

Over-fitting Always Occurs?

i get stuck in one sentence in machine learning. i read tom Mitchel book on ML, and some other materials. if we have small training set, always over-fit can occurs? or is likely to occurs? i read ...
-1
votes
1answer
40 views

Policy function π in Reinforcement learning unclear

I have one question about policy function in Reinforcement learning. in fact this function indicates which action should be done in each state? Or this function indicate for get the ...
1
vote
1answer
22 views

Matching training with Neural Network

I have a matching algorithm that is based on making an comparison score. This score is divided into parts. Example: 5 - Points for attributes (lets say they have 3 common attributes, would the score ...
-2
votes
1answer
43 views

Neural Network Design Challenge

i'm studying for PHD Entrance Exam on Stanford. one of previous material exam designed very challenging. i want to design a NN for classifying following 2-class problem. 1) output should be -1 or ...
1
vote
0answers
17 views

basic doubt on policy iteration

consider the policy iteration algorithm for a finite state MDP. Suppose the initial policy is a stochastic policy. Now, can the optimal policy be deterministic after improvements ? Or, can we say that ...
0
votes
1answer
97 views

Bayesian Nets & Markov Blanket

As i passed PHD entrance exam, some days ago, i want to find solutions for challenging problem. In Bayes network on X={X1,...Xn} each random variable has P parents and Q child's. for Xi we want to ...
0
votes
0answers
30 views

Can anyone help with a simple neural net I am trying to code?

I have a neural net with two input units (and a bias) connected to four hidden units, with each input unit (including the bias) connected to all the hidden units. Then there is one output unit. All ...
2
votes
1answer
47 views

Q-learning in a Dynamic environment

I am new to reinforcement learning. Lately, I have learned Q-learning using the following tutorial. Is Q-learning still possible if the environment is dynamic. Using the environment of the tutorial ...
0
votes
1answer
105 views

What would show a human mind is/is not reducible to a Turing machine?

In computer science it is often assumed that a human mind can be reduced to a Turing machine. This is the assumption that underlies the field of artificial intelligence. However, it is an ...
0
votes
1answer
28 views

What does “finding an optimal action” for a bandit mean?

In Sutton and Barto's reinforcement learning book, in multi-armed bandit problem a phrase has been used. "finding an optimal action" using greedy/$\epsilon$-greedy algorithm. When it is said that an ...
1
vote
1answer
33 views

Robot follows a path near an obstacle without colliding

I have a problem that I would like to solve it. A robot have to move near an obstacle (e.g a wall) without colliding. He should also try to be always near the obstacle. The following picture can help ...
-3
votes
2answers
92 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
23 views

Are these CNF clauses for at most one and the same correct?

Given Boolean variable Xij that represents whether dog i is kept in kennel j. Encode in CNF clauses: Dogs that cannot be kept together must be kept in separate kennels Here is what I ...
0
votes
0answers
289 views

Haar cascade vs Lbp cascade vs Hog Cascade in object detection

I am doing an project about recognizing one kind of leaf. Well I am using Emgucv with visual stduio 2010 c#. I have read about using 3 differente features extraction but I do not know when I can use ...
1
vote
0answers
14 views

What types of images should I use for negative examples in a classification problem? [duplicate]

I am doing a project to recognize a kind of leaf using ANNs with Emgu CV in C#. My project is to get frames from camera then present them to the ANN and have the ANN tell me if that frame contain a ...
0
votes
1answer
63 views

Optimality of A*

I read in the artificial-intelligence book of Russel and Norvig that The tree-search version of A* is optimal if heuristic function is admissible, while the graph-search version is optimal if ...
0
votes
0answers
41 views

What level of maths do I need for artificial intelligence? [duplicate]

I want to learn maths for artificial intelligence. I heard that main areas of mathematics for AI are Multivariable Calculus, Linear Algebra, Probability and Statistics and Discrete Mathematics. But ...
0
votes
1answer
50 views

AI approach for exploring a static grid environment [closed]

I have a grid environment which contains in each cell a static agent. When my agent enters a cell, the static agent in this cell might take points away from me, give me points, or do nothing. My agent ...
1
vote
0answers
51 views

Research Papers about Production Systems for Solving Algebraic Equations

I'm interested in coding up a small project that solves uni-variate algebraic equations (up to cubic) by simulating the actions of a human expert in solving the equation. To do this, I've drafted a ...
-1
votes
1answer
48 views

In back propagation why is this necessary, o (1 - o) [duplicate]

To calculate the error in back propagation you would use, (target_output - actual_output) * actual_output * (1 - actual_output) So what does, actual_output * (1 - actual_output) solve? Wouldn't, ...
1
vote
1answer
89 views

How are Bayesian Nets, Hidden Markov Chains, Conditional Random Fields and Neural Nets related?

I am having an AI exam in two weeks, and I am still figuring out certain concepts and ideas, related to Bayesian Nets, Hidden Markov Chains, Conditional Random Fields and Neural Nets (yes it is all ...
3
votes
1answer
97 views

Why is the initial state of Zobrist hashing random?

When generating a board for Zobrist hashing, why are the initial elements random? How can you detect changes to elements later if the initial values are random?
-1
votes
3answers
81 views

Is human being a Turing Machine?

We may not have a determinate answer to this question. But is there any evidence for or against this question? Or is there any study on it?
1
vote
1answer
42 views

Recognizing Horn clauses

I am currently studying model theory and I am trying to decide if a clause is a Horn Clause. I know that a Horn Clause is a clause with at most one positive literal, but there are some clauses that it ...
0
votes
0answers
26 views

Does using diploid (dominant/recessive) genes in genetic algorithm offer any advantage? [duplicate]

I've been looking into diploid genetic algorithms for a while. Although, it seems like an implementation which includes diploid (dominant/recessive) genes is closer to the implementation that has ...
12
votes
2answers
77 views

What are the state-of-the-art algorithms for pathfinding on a continuous map of the Earth?

Suppose I have got a solar-powered autonomous surface vessel somewhere in the fjords of Norway, supplied with a fairly recent set of maps, a GPS receiver, and no means of downlinking detailed commands ...
13
votes
2answers
67 views

A scoring approach to computer opponents that needs balancing

Update: The (Java) code used for this approach has now been posted at Code Review. This question is about an approach to computer opponents that I have created and are either currently being used, ...
2
votes
1answer
85 views

Is Q-Learning ever better than Brute Force?

I am currently learning about the Q-learning algorithm, so I therefore assume that it has some use or purpose. However I currently cannot see how it is in any way useful. In terms of complexity class, ...
-3
votes
2answers
40 views

Description of “Logistics Domain” in AI

While reading some papers in AI (for a project I have to do), I see expressions "blocks world domain" and "logistics domain". I know what blocks world domain is, but I don't know the definition of ...
13
votes
3answers
71 views

How to use Artificial Intelligence in Computer Chess

In some (historical) papers, chess has been referred to as the drosophila of artificial intelligence. While I suppose that in current research, the mere application of a search algorithm is at best ...
3
votes
1answer
73 views

Are expert systems outdated, what are better alternatives to them, if any?

I need to link facts to actions through rules. If a person bought soup 10 times and he is coming at midday every day, then the system should link the fact that the person bought soup so many times, ...