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
votes
0answers
15 views

Machine learning algorithms for abbreviations & acronyms dictionaries

https://play.google.com/store/apps/details?id=com.farlex.abbreviations https://www.google.com/search?q=abbreviations+dictionary&oq=abb&aqs=chrome.0.69i59j46i39j69i59l2j69i57.5612j0j7&...
0
votes
0answers
21 views

Is machine learning and AI all about pattern recognition?

I realized that machine learning and AI is mostly about spamming the auto correlation and cross correlations from mathematics and combining them with memory arrays. Is it right? What do you think ...
1
vote
1answer
17 views

How to get a heatmap of pixel influences from a Convolutional Neural Network

If I have a CNN model (let's say I'm using Tensorflow and Keras) that I've trained for a particular task. For example, let's say I've trained it to detect the difference between an apple and banana. ...
2
votes
1answer
66 views

What is the purpose of learning propositional logic

I am in an AI class where we have extensively learned about propositional logic. I am wondering what the point of learning this is? Are there any uses for propositional logic? Beyond basic logic gates ...
0
votes
0answers
25 views

Is deepfake detection viable?

I'm thinking of doing a project on deepfake detection, but I'm not entirely sure if it is viable. Based on my understanding, how it works is that deepfake generation programs have a generative and ...
0
votes
0answers
21 views

How to find unary potential in belief propagation algorithm for Markov Random Field with a tree structure?

Given that I have a Markov Random Field with a tree structure, which means that belief propagation (or sum product) algorithm will give me the exact solution when I query for marginal probabilities. I ...
2
votes
1answer
32 views

object image segmentation

I have 2 different datasets with similar objects, one where each object is 50 pixels wide and the other where they are 150 pixels. Each photo is 512x512 for both datasets. These two datasets have the ...
0
votes
0answers
51 views

Creating An Artificial Universe

This is a general question and one that has bugged me for a long time. I want to start working on an artificial universe, not something too ambitious but more of a basic concept. What I have in mind ...
0
votes
0answers
25 views

About the complexity of deciding if the closed world assumption for renamable Horn CNF is consistent

Let $T$ be a theory that only contains renamable horn formulas. What is the complexity of deciding if the closed world assumption $CWA(T)$ is consistent? The closed world assumption is defined as ...
0
votes
1answer
44 views

How are prime implicates of HORN-Formulas defined?

I'm confused about the definition of prime implicates in Horn formulas. For example in the paper of Kira 2012 on page 109 it is stated: Now in the paper of Boros 2010 on page 82 the following ...
1
vote
1answer
66 views

Why do AI researchers seem to think that consciousness is a computation?

Disclaimer: I am just an undergraduate student so my exposure to a lot of things is certainly limited. I am not sure about the actual popularity of the idea that consciousness is a computation but my ...
-1
votes
1answer
33 views

Begin with AWS or Azure ML Course? (or something else?)

I tend to see a lot of ML/AI/DL courses everywhere. Having no background in either of these, I am confused about what to do and where to begin. I was suggested to have a look into the Stanford Andrew ...
0
votes
0answers
28 views

Situation calculus: how to find pre-conditions in 15-puzzle game?

I have been working on finding the preconditions for a situation calculus example for some time now. This example is called the game "15-puzzle" where you can find a discription here https://...
2
votes
2answers
58 views

Books for the Mathematical Theory of AI/ML

I am interested in the mathematical foundations of Artificial Intelligence and Machine Learning. Are there any books which will describe and present the mathematical foundations in detail? I am not ...
0
votes
0answers
35 views

Delta rule for binary step function

I have a question of understanding about the Delta Rule: $\Delta w_i = (y - \hat{y}) \times x_i$ Why does $x$ have to be multiplied again after the difference? If the input is $0$, the product of $w$...
0
votes
1answer
22 views

Is there any way that I, a CLI PHP developer, could “hook into” some kind of AI blackbox?

For many years now, I have heard about "AI" and "neural networks" and all these buzzwords, and it is regularly claimed on Slashdot that this or that open source program is able to "do AI". But then I ...
1
vote
2answers
31 views

Retrieving data from website - Parser vs AI

I'm currently working on a personal software project (as a hobby) and would like to know which kind of approach I should follow according to you. My application scans some websites (like Amazon or ...
2
votes
2answers
64 views

How can I treat a problem like a search problem in AI?

I'm a CS student and I'm trying to understand the searching algorithms used in AI. My problem is that I don't really understand how to treat a problem like a search problem. I don't know which would ...
0
votes
0answers
25 views

Search algorithm for vehicles moving through a square grid

I started to learn AI and I'm trying to solve the following problem like a search problem and I'm wondering which search algorithm would be the best in this case. Please give me at least some tips, I ...
0
votes
1answer
37 views

Face recognition system with a sparse dataset

I have a dataset of 100 ID's, each ID with only a single unique face image. How can I develop an effective face recognition system to recognise only these faces? I was thinking Deep Learning but the ...
0
votes
1answer
33 views

Performing semantic segmentation on images on word documents

At the moment, I'm making a comparative analysis between two different neural networks for a class. The problem they are both trying to solve is detecting tables on documents. Below is an example of ...
1
vote
2answers
37 views

Calculate the number of models of a KB

Suppose we had a domain with two individuals, $x$ and $y$. Suppose we had two predicate symbols $p$ and $q$ and three constants $a$, $b$, and $c$. Suppose we had the knowledge base KB defined by: ...
0
votes
0answers
21 views

How to get synonyms from definitions using Bayes algorithm

I work on a project: an online dictionary where the user can find definitions of a word he's looking for. My supervisor asked us to add synonyms using machine learning. He recommend us to use Bayes ...
3
votes
4answers
181 views

Are all computer viruses man-made?

I'm curious if the origin of any successful computer virus is known to NOT have an intentional, human originator. To put it another way, do computer viruses ever "spontaneously" originate through the ...
1
vote
2answers
28 views

Time efficient way to implement Multi-Armed-Bandits?

I'm doing a research on Multi-Armed Bandit (MAB) problem with approx. 1 million arms. In contrast, the number of iterations is of course much larger, about 10-20 million. Most MAB-algorithms require ...
0
votes
1answer
39 views

Is Artificial intelligence simply taking decisions on the basis of values produced by a machine learning model

I am researching on AI and its working. Whenever I try to search for AI algorithms, ML algorithms come up. Then, I read the differences between ML & AI. One of the key points mentioned was "AI is ...
0
votes
0answers
25 views

Coding a Binary Constraint in Python

I am working on a CSP solver in python, and am stuck how to code the constraints. According to my assignment, the constraints are given through an input file, and can contain operators such as <, >,...
2
votes
0answers
58 views

Sample applications based on First Order Logic

I often hear about benefits of FOL, but I wonder what are some of its real world applications? Could someone please provide samples/case studies of applications of FOL that address real world ...
1
vote
2answers
60 views

What is the meaning of the mutation rate in genetic algorithms?

Let us suppose that we have a mutation rate of 5%. What does this mean? Each gene of each individual has 5% of probability of change to another value? At the end, around 5% of the genes of each ...
0
votes
1answer
61 views

Approximating Deep Neural Networks (DNNs) with Binarized Neural Networks (BNNs)

I am working currently as a research intern on Binarized Neural Networks where the weights and the activations of the network are binary. The architecture of this type of networks makes them memory ...
2
votes
2answers
99 views

Being stuck and frustrated with my masters project

I'm doing a masters in CS that requires me to implement from scratch most of the neural network models and because python libraries aren't applicable to what i want. The problem is that i don't feel ...
1
vote
0answers
15 views

Good AI model for learning to write code, specifically generate css from any given html?

Currently I am working on getting lots of html code and its related css, via id or class name. Once I have enough data to work with I am unsure how it would be easiest for any model to learn what css ...
0
votes
0answers
24 views

Why does my EM algorithm not converge?

Any ideas why my likelihood probability for this EM algorithm doesn't converge (have slope of 0) to "find" the three clusters? I've tried increasing the iterations, which makes the slope nearly ...
0
votes
1answer
28 views

Confused on Variational AutoEncoder

I'm a bit confused on how Variational Autoencoders are trained. In particular I'm confused on how the latent variable is generated for each input. My questions are as follows: When running ...
2
votes
2answers
65 views

Need recursive version of Conflict based backjumping

I am implementing conflict directed Backjumping algorithm of prosser in java. But, the algorithm is iterative approach. How can it be built with recursive approach? In AIMA they give the recursive ...
0
votes
0answers
20 views

Training a model from self-play

Say I'd like to build a Go AI. The Go AI takes in the board state and then predicts who's more likely to win from that state. When I want to make a move, I just test every next board state I could ...
2
votes
1answer
155 views

Why is IDA$^*$ faster than A$^*$? Why does IDA$^*$ visit more nodes than A$^*$?

I used IDA$^*$ for optimally solving the 8-puzzle and my friends used A$^*$ for it too (with same manhattan distance heuristic). I calculated the average running time and number of nodes of my ...
9
votes
4answers
400 views

How to devise an algorithm to generate a random but valid train track layout?

I am wondering if I have quantity C of curved tracks and quantity S of straight tracks, how I could devise an algorithm, (computer assisted or not), to design a "random" layout using all of those ...
0
votes
0answers
17 views

What does the gradient mean in evolutionary algorithm?

I have been reading about evolutionary algorithms and I often find the concept of gradient that is used as "to follow a gradient"...
1
vote
2answers
32 views

Multi-agent randomized behavior

In Artificial Intelligence: A Modern Approach Edition 3, Page of 43, At Single Vs. Multi-agent section's last line, Writer says, In some competitive environments, randomized behavior is rational ...
1
vote
1answer
49 views

General resolution in first order logic

Assuming you have a formula in first order logic like $$(\forall_x p(x) \land \forall_x q(x)) \rightarrow \forall_x(p(x) \land q(x))$$ (which seems valid?) Converting the formula to ...
12
votes
4answers
17k views

Water Jug Problem in AI

In AI we can classify a problem in 3 classes, ignorable, recoverable or irrecoverable problems. Now while reading Water jug Problem I am wondering in which of these 3 class it should fall? It should ...
0
votes
1answer
49 views

How does image reconstruction take place in neural network?

I am reading through and thinking about how neural network works and have been reading about convolutional neural networks (CNN). I am particularly interested in image filtering (or enhancing) using ...
3
votes
2answers
137 views

Human brain vs computer

I am looking for a problem that can not be solved by computer but can be solved by human while computer can verify if the answer is correct or not. In fact what is the question in my head is that is ...
1
vote
1answer
768 views

Chinese room test vs Turing Test

So, I took up a new course (AI) in my uni and came across these two test $TURING$ $TEST$ and $CHINESE$ $ROOM$ $TEST$. But I am not able to understand is the Chinese room test really accurate? Does it ...
-1
votes
1answer
39 views

support vector machine values

Does anybody knows how to calculate w1 and w2 and b . I have the formula but I have no idea where those numbers come from . my question has solution so it is not a home work because the solution of ...
0
votes
1answer
57 views

Is it possible to use “and”, “or” “not” as relation/predicate in an ontology? In order to represent causality?

If we use an ontology we can represent knowledge, using notably semantic triple <s,p,o>. I was wondering how can I represent this: A and B cause C or A ...
2
votes
2answers
31 views

Neural network game players and incremental updates

Neural networks in recent years have been successfully used for gameplaying. A difference between games and e.g. image processing is that the game boards get updated incrementally. Do any neural ...
0
votes
2answers
57 views

Why does a RNN network output different based on the training sequence

I've set up an RNN LSTM network in Java using DL4J as the library. I currently have 500 examples of positive text, and 500 examples of negative text. When I fitness the training data by first ...
1
vote
1answer
95 views

Are chatbots a good example of overfitting?

In my highschool class we are learning about Artificial Intelligence, and especially the problems that come with machine learning. I was wondering if chatbots like cleverbot were good examples of ...

1
2 3 4 5
10