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
0
votes
1answer
36 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 ...
0
votes
1answer
36 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
1answer
1k views

Understanding the Broyden–Fletcher–Goldfarb–Shanno Algorithm to Select Weights for Neural Nets

I am trying to train and implement a Neural Network. I was reading a few articles, learning about their principles and the math that goes behind them. However, while I was trying to understand the ...
1
vote
1answer
15 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
46 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 $\...
0
votes
1answer
32 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 ...
3
votes
2answers
1k 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 ...
0
votes
0answers
15 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
53 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 ...
0
votes
1answer
34 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 ...
1
vote
2answers
49 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 ...
5
votes
3answers
18k views

When would best first search be worse than breadth first search?

I am studying best first search as it compares to BFS (breadth-first search) and DFS (depth-first search), but I don't know when BFS is better than best-first search. So, my question is When would ...
0
votes
1answer
17 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
91 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 ...
2
votes
2answers
51 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 ...
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
20 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 ...
2
votes
2answers
30 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 ...
1
vote
0answers
378 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: ...
11
votes
2answers
14k views

What is Least-Constraining-Value?

In constraint satisfaction problems, heuristics can be used to improve the performance of a bactracking solver. Three commonly given heuristics for simple backtracking solvers are: Minimum-remaining-...
1
vote
2answers
2k views

Effect of value of k in K-Nearest Neighbor

In K-Nearest Neighbor the value of k decides the accuracy of classification. What are the pros and cons of choosing smaller value for k and larger value for k?
0
votes
0answers
17 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 ...
1
vote
2answers
27 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 ...
9
votes
4answers
388 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 ...
5
votes
1answer
180 views

Predicting next action to take to reach a final state

Does anyone know of an algorithm that could be used to determine the next action to take to reach a desired state when trained on time-series data? For example, a robot starts at a certain state, ...
0
votes
1answer
34 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 ...
2
votes
1answer
104 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 ...
1
vote
2answers
58 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
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"...
3
votes
2answers
125 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 ...
2
votes
1answer
38 views

How are image processing and computer vision related to artificial intelligence.?

We have often heard both terms image processing and computer vision in AI sessions But i am confused, how they both are related to artificial intelligence?
1
vote
1answer
48 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
16k 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 ...
3
votes
2answers
804 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
1answer
477 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 ...
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 ...
1
vote
2answers
185 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 ...
0
votes
2answers
48 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
66 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 ...
0
votes
0answers
13 views

Clustering - Complete Linkage draw example

I'm studying unsupervised learning methods (clustering) and i've seen the Complete Linkage Method. I've also seen the following statement: Unlike single linkage, the complete linkage method can be ...
1
vote
0answers
117 views

What are the differences and similarities 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
2answers
72 views

Assuming an infinite amount of computing resources, would the minmax algorithm always win in chess?

The minmax algorithm is a popular strategy used to design chess engines. Usually, since the state-space of chess is huge, we choose a fixed depth and evaluate the game tree down to that level, and ...
1
vote
0answers
21 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 ...
5
votes
1answer
547 views

How did the Logic Theorist prove the Pons Asinorum?

I was reading about the Logic Theorist proving many of the Whitehead and Russell's Principia's theorems. However, I cannot find any technical explanation on how the program proved those theorems and ...
1
vote
1answer
111 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
3k 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 ...
4
votes
2answers
403 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
635 views

Use Machine Learning to predict when a Gas Station is running out of fuel

We have years of data on several Gas-Stations. Data about the Gas-Stations: the number of tanks, Gallons per tank, Location, number of pumps, kind of fuel, etc. Data on fuel consumption for x gas ...
0
votes
2answers
2k views

AC-3 Algorithms on CSP problem, What is happened when enocunter to an empty domain variable?

Suppose We Applying Arc-Consistency (AC3) algorithms on one Constraint Satisfaction Problem, if domain of one variable be empty, what is the next step of this algorithm? According to This Link and to ...
5
votes
1answer
3k 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, ...

1
2 3 4 5
10