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
0answers
16 views

Value flow (and economics) in stacked reinforcement learning systems: agent as reinforcement environment for other agents?

There is evolving notion of stacked reinforcement learning systems, e.g. https://www.ijcai.org/proceedings/2018/0103.pdf - where one RL systems executes actions of the second RL system and it itself ...
0
votes
0answers
15 views

Is fear memory storage in brain a good research topic for a computer science research? [on hold]

I'm a Computer Science Masters student. Recently my thesis supervisor proposed me a research topic on which I can work for some years and continue my Ph.D. on same topic. The topic is: ...
0
votes
0answers
21 views

How to implement backjumping algorithm with java? [closed]

I have know that backtracking algorithm uses recursive to backtrack.But,in backjumping they backtrack more than one level.If so,how do I get idea to jump more than one level .
1
vote
0answers
10 views

What are the differences between CYC and IBM Watson?

From what I gathered from Wikipedia, CYC is based on set membership logic. So it would take symbols and create set membership predicates. But how is this different from IBM Watson?
0
votes
0answers
4 views

How do I input (magnitude of) numerical data in CNN/U-net like architectures?

I've been given some (latitudes,longitudes) points with cellular signal strength(float numbers) on those particular points. And I've been given the location, (lat,longs) of cellular towers in a ...
1
vote
1answer
47 views

Search vs planning in artificial intelligence

I'm studying artificial intelligence following the Russell & Norvig book. We did a search and planning part that for me is the same (at least on the representation). I'd like to know what is the ...
3
votes
2answers
35 views

How do you prove a heuristic is admissible?

How does one prove that a suggested heuristic is admissible? Is this even possible? For Example: Let's say I have the game Free Cell. Rules: https://en.wikipedia.org/wiki/FreeCell How can I ...
0
votes
0answers
7 views

What is the difference between behavioural cloning and imitation learning?

What is the difference between behavioural cloning and imitation learning? I am getting quite conflicting responses: https://medium.com/@paichul/building-driving-assist-system-part-1-f7fb9278670c ...
1
vote
0answers
39 views

Multi Agent Sokoban Solvers state of the art

I am researching into coding a solver for a variant of the Sokoban game with multiple agents, restrictions (eg. colors of stones, goals) and relaxations (push AND pull possible etc.) By researching ...
0
votes
2answers
25 views

Don't understand minimax algorithm in terms of chess

I'm new to minimax algorithm, but i understand it's entire concepts as it's easy, my biggest issue is understanding it's implementation to my chess game, no internet solution answers this question ...
0
votes
0answers
13 views

are there any other strategies used in connect 4 and are they better or worse than minmax with alpha beta? [duplicate]

Just curious about ai strategies that people use for connect 4 besides minimax with alphabeta pruning because I see a lot of people using minimax + evaluation in the internet. Are there other ...
1
vote
0answers
64 views

Law as a computer science problem?

For a long time, computer scientists and logicians have noticed that law (statutes, contracts, adjudication, etc), has some similarity with formal logic and programming languages, and have approached ...
0
votes
2answers
206 views

The barbers paradox first order logic formalization

I tried to look on the site and while I found some similar questions, I did not find the first order logic formalization of the following sentence (the basic barber's paradox), so I wanted to ask if I ...
0
votes
0answers
27 views

Sorting using AI / neural net

I have a search operation taking place on a server that essentially queries images using OpenCV against other images from a database. Since each image query ...
1
vote
1answer
21 views

List of all possible reasoning tasks - satisfiability and theorem proving only?

What is the exhaustive list of reasoning tasks? As far as I can understand, then any logical reasoning reduces to 2 tasks only: 1) satisfiability problem (finding the assignment of the variables) and ...
0
votes
1answer
71 views

How to find the best exploration parameter in a Monte Carlo tree search?

I've developed a Monte Carlo tree search algorithm in checkers. Here is my question. What should be the value of $C$, the exploration parameter in the following formula described in Monte Carlo Tree ...
1
vote
1answer
51 views

Two Minimax AIs playing against each other

I am trying to have my Minimax AI chess players play against each other. I was a bit confused about an implementation detail. Let's call black my first minimax AI ...
0
votes
0answers
43 views

How to perform particle swarm optimization clustering of results obtained from tf-idf vectorizer?

I have a collection of news articles. I have performed tf-idf operations on them. I am using python as programming language so it was just the use of TF-IDF vectorizer function. I now have the ...
1
vote
0answers
19 views

How to go about designing a quiz that changes difficulty based on user performance?

I thought about using a machine learning algorithm to learn the performance patterns of the quiz taker and model the next quiz based on how he/she performed. So each question will have a difficulty ...
1
vote
0answers
30 views

general question about linear algebra [closed]

have new discoveries been made in linear algebra since the dawn of AI or was it all "laid out" for the computer scientists by former mathematicians?
2
votes
2answers
55 views

Does an optimal path imply the heuristic is admissible?

If we are given an A$^*$ path search with some heuristic $h$ that yields an optimal path, without knowing that the heuristic is admissible beforehand, would this imply that $h$ is admissible?
0
votes
1answer
25 views

How do we fix area of detectors in object detection?

I have gone through various articles on medium and also some from other sites trying to understand SSD. I am able to figure out most of the things from articles except this one. They always say that ...
0
votes
0answers
15 views

What's the difference between size ordering/ data ordering/ least recently used rule?

What's the difference between size ordering/ data ordering/ least recently used rule? I did lots of researches already, and most of the books say: Data ordering: Arrange all possible assertions in ...
1
vote
2answers
45 views

Learning a perceptron from stream data

I want to train a Perceptron using stochastic gradient rulefrom the stream data. I have very limited amount of memory and i can store only $N$ examples. Suppose my population consist of point as ...
0
votes
0answers
120 views

How MAC-3(maintaining arc consistency-3) algorithm works?

I am studying CSP problems in artificial intelligence. I don't understand the MAC-3 algorithm especially line number 10. Could you tell me with step by step? ...
1
vote
1answer
45 views

Search on Conformant Problem: solution for subset of a belief state

I am having trouble understanding the following statement. I have understood why in a sensorless/conformant problem, if there exists a solution (a sequence of actions) for a belief state $b$, then it ...
0
votes
0answers
21 views

Value iteration in MDP - updating each state once per inner loop?

In value iteration algorithm we update the utility of all possible states ("for each state update its new utility"). After we've updated all states we check to see if the delta is smaller than some ...
1
vote
2answers
58 views

Choosing heuristic for A* algorithm where cost is less than absolute distance

Looking for information on choosing a heuristic for instances where the cost of traversing an edge can be less than one. For example, say movement is allowed in the cardinal directions. Should all ...
0
votes
0answers
21 views

Relevance of the ZeroSum game to Heuristic search?

A question was posed to me as to the relevance of the ZeroSum game to Heuristic search algorithms. I know that the zero sun game is a theory in which one persons gain is exactly balanced to another ...
1
vote
0answers
97 views

Is MCTS an appropriate method for this problem size (large action/state space)?

I'm doing a research on a finite horizon decision problem with $t=1,\dots,40$ periods. In every time step $t$, the (only) agent has to chose an action $a(t) \in A(t)$, while the agent is in state $s(t)...
0
votes
1answer
59 views

Real world applications of first order logic

I study an AI course and we done some lectures about first order logic and the first thing that I was thinking is, what are the real world applications of first order logic and generally logical ...
0
votes
0answers
72 views

Genetic Algorithm - likely population of parents after roulette-wheel selection

Below is a question from a past paper that I am attempting to understand in preparation for an exam. Am completely stuck on it. Would appreciate any pointers in the right direction. How do we go ...
0
votes
1answer
39 views

Optimality of A* search

I use the A* search algorithm to to search for the shortest path from S to G. The evaluation function is $f(n) = g(n) + h(n)$. Since node A and B have the same estimated total cost, I choose to go ...
0
votes
0answers
23 views

How many states are examined in the most wins heuristic for tic-tac-toe (9-grid)?

I'm new to AI, and have a hard time to understanding how to count the total states are examined in the most wins heuristic for tic-tac-toe two plys deeper(9-grid)? Need help
2
votes
1answer
67 views

Does domination rule apply for inadmissible heuristics?

Let's say $h_1(n) \geq h_2(n)$ so that dominance is established even if $h_1$ and $h_2$ are both inadmissible/non-optimal heuristics -in whichever given search space. Is $h_1$ still faster/better ...
2
votes
0answers
18 views

Why aren’t (type theory based) automated theorem provers efficient?

Note: my main experience with theorem provers is with Type theory based proof-assistant, rather than an actual automated theorem prover. It is obvious why naive automated theorem proving is ...
2
votes
1answer
42 views

Is Artificial General Intelligence possible with our current machine learning models? [closed]

In other words, is artificial human level intelligence not possible yet just because of limitations in processing power and amount of data required to train the models? Or we don't have the knowledge ...
1
vote
0answers
202 views

understanding constraint satisfaction problem: map coloring algorithm

I am trying to implement this recursive-backtracking function for a constraint satisfaction problem from the given algorithm: ...
0
votes
1answer
30 views

Steps to create a heuristic for solving a problem

I am completely new to AI and doing self-learning to acquire this knowledge. I went through the different available search algorithm like BFS, DFS and A* but something that I can't understand is a ...
2
votes
1answer
77 views

Proving Monotonicity of Softmax Layer

In the book here: http://neuralnetworksanddeeplearning.com/chap3.html If you scroll down to Exercise 2 in the Softmax Section, it says Show that $\partial a^L_{j}/\partial z^L_{k}$ is positive if $...
1
vote
0answers
34 views

What are good examples of computational theories for A.I. according to David Marr's Definition?

I was reading David Marr's "Artificial Intelligence-A Personal View" and he talks about "computational theory of AI" or what he laters labels as "Type 1" Theory. He provides the example of Chomsky's ...
2
votes
1answer
50 views

Understanding Alpha Beta Pruning: Why do we ignore the values of a unsearched tree after the first leaf, can they not include acceptable values too?

So this is my question. I am trying to understand this part of the book: At d) why do we stop looking at the other nodes in that branch? There could be a acceptable value next to the 2? I am just ...
1
vote
1answer
62 views

Artificial intelligence and undecidibility

Can artificial intelligence solve problems like Post correspondence problem?
1
vote
1answer
13 views

Are there existing extensions to behavior trees that fascilitate node communication?

I've been looking into behavior trees, but I cannot find a lot about them. The Wikipedia page pretty much only mentions sequence and selector nodes. I have found implementations that also provide ...
2
votes
1answer
44 views

The task of recognizing game units in the screenshot

I'm new to computer vision and I want to solve the task of recognizing the game units of the game Clash Royale in the screenshot. Briefly, there are about 70 different types of gaming units belonging ...
1
vote
1answer
78 views

Rational versus intelligent agents

Question about "Artificial Intelligence: A Modern Approach by Russell and Norvig" I have issue to distinguish clearly between intelligent and rational agent presented by Norvig and Russel. What I ...
0
votes
1answer
35 views

Formal definition of loss surface of multi-layered networks

Let $\mathcal{L}$ be a loss function associated with a multi-layered neural network. So it seems almost everyone in AI/ML community is interested in the Hessian $H=\partial^2 \mathcal{L}$ of $\...
3
votes
1answer
74 views

How do you protect an AI from a human doing “illogical” moves?

Using a monte carlo approach and evalutation function. Some moves will deemed to be more advantageous than others. As a computer plays itself, it will generally go for the best moves possible. And ...
0
votes
0answers
139 views

Reverse engineering a neural network

Suppose we have a neural network (such as google uses for instance) which detects an object in images, which could be a cat or car. Suppose that it is instead an alien artifact that we dont have ...
0
votes
0answers
15 views

Which area of research is the logical successor to Minsky's society of mind idea?

I'm curious if there is any body of research that could be considered as the logical successor to Marvin Minsky's "society of mind" idea? It seems as if the notion of agents plays a crucial role in ...