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
-2 votes
0 answers
48 views

Help me derive the empty set from this horn clause

Consider the below set S of Horn clauses. P(a) ¬P(x) ∨ P(s(x)) ¬P(x) ∨ Q(x) ¬Q(s(s(a))) Here, P and Q are predicates, a is a constant, x is a variable, and s is a unary function symbol. The clauses ...
user avatar
  • 1
-3 votes
1 answer
27 views

Which algorithm would be most suitable for finding a minimum subgraph that connects all vertices in a graph and has the smallest weight?

Which algorithm would be most suitable Kruskal, Prims or Steiner tree algorithm ?
user avatar
  • 1
1 vote
0 answers
10 views

Does AC-3 algorithm decide a CSP?

If AC-3 algorithm returns an empty domain, we know for sure it cannot be solved. But given that it returns only domains with at least a variable in it, do we know the CSP is solvable?
user avatar
  • 11
1 vote
1 answer
59 views

When to stop training a back propagation algorithm based on the MSE?

I have a fully connected neural network that consists of 3 inputs + bias, 4 neuron hidden layer, and 2 layer output, I am using the sigmoid activation function on the hidden layer only and use the ...
user avatar
0 votes
0 answers
8 views

Sequential State Minimal Logic Synthesis?

There is a lot of work on combinational logic synthesis, but very little on sequential logic synthesis and even less work on minimum complexity sequential logic synthesis. This, despite the ...
user avatar
1 vote
0 answers
10 views

Blackwell-Rao applications to Machine Learning and AI

We learned recently in a graduate statistic course about Blackwell-Rao of an unbiased estimator statistic T; other methods for parameter estimation includes Maximum Likelihood and Method of Moments ...
user avatar
  • 111
0 votes
0 answers
13 views

How does TRANSFORMER DECODER WITH MEMORY-COMPRESSED ATTENTION work?

I came across TRANSFORMER DECODER WITH MEMORY-COMPRESSED ATTENTION (T-DMCA) model in the paper "GENERATING WIKIPEDIA BY SUMMARIZING LONG SEQUENCES" (https://arxiv.org/pdf/1801.10198.pdf). ...
user avatar
0 votes
0 answers
20 views

What is the best way to predict a continuous score based on image characteristics(pixels)?

I have a dataset with 9912 images, what is the best way to train them based on the pixels and features of the images to be able to predict a continuous target ranging from 1 to 100? The goal is to ...
user avatar
  • 1
2 votes
0 answers
86 views

What is ridge in hill climbing algorithm?

I am studying hill climbing algorithm and this topic seems so confusing. What is ridge basically? Can you show an example while searching using hill climbing when ridge occurs? I have researched in ...
user avatar
1 vote
1 answer
128 views

Uniform Cost Search with Backtracking / Additional constraint?

I am able to implement the default uniform cost search (python) to find the shortest path between two nodes (path cost). I followed this pseudocode: Now, I want to calculate the shortest path with ...
user avatar
0 votes
1 answer
36 views

Is there an AI algorithm that generates 2D vector graphics art like this image?

Is there an AI algorithm that generates 2D vector images with given examples like the the below images that is accessed on a website or something?
user avatar
0 votes
1 answer
38 views

Using an optimal number of agents, maximise coverage of an area while minimising distance travelled

I'm a CS Year 2 student working on a team project which requires a solution to the following problem: Given a starting position on the edge of an irregular shape (example above) and a maximum number ...
user avatar
-1 votes
1 answer
46 views

How to find time complexity of Breadth First Search for this tree?

This is what I got from another forum, but honestly doesn't make much sense to me. Time complexity for a single tree doesn't make a lot of sense, since the function in the big O notation might be ...
user avatar
2 votes
1 answer
17 views

Clarification about RNN encoder-decoder equation

In the paper by Cho et.al., section 2.3 details the equations for the modified LSTM cell in RNN used in the paper's implementation. The equation in question is : Here, the output of the reset gate (r)...
user avatar
0 votes
0 answers
17 views

Radial Basis kernel producing the same decision boundary as a Linear kernel

The following question is from the MIT 6.034 2006 Final Exam paper. In answering part 6.5, I wasn't certain why the radial basis kernel would produce the same decision boundary as a linear kernel (...
user avatar
  • 1
2 votes
1 answer
41 views

Resolution algorithm does not seem to generate the empty clause

Let's assume I have the following 3 clauses: $\neg T$,$\neg Q$, ($\neg P \lor Q \lor S \lor T)$,$(\neg U, T, \neg S)$,$(\neg U, T, P)$ and I want to see if our KB entails $\neg U$ so I tried to apply ...
user avatar
0 votes
0 answers
10 views

Is there complexity hierarchy of worlds/environments that are used for simulation or reinforcement learning in AI?

Is there complexity hierarchy of worlds/environments (i.e. state space * action space) that are used for simulation or reinforcement learning in AI? Hierarchy like ...
user avatar
  • 1,351
1 vote
1 answer
49 views

How to think about heuristics

I have a game about drone delivery company. The game consists of a rectangular map, which contains tiles that cannot be passed. I can control a certain amount of drones, each one of them starts at a ...
user avatar
  • 131
0 votes
0 answers
7 views

What are the axioms in the Semantic Networks

The Professor has given us a Assignment and Has asked us to tell the axiom that is used to define the semantics of the semantic network of one Particular example, the issue is I have no Idea what ...
user avatar
  • 1
0 votes
0 answers
15 views

Random initialization of weights

I have trained a neural network using a train and a validation dataset.I used the validation dataset for hyperparameter and architecture optimization.I split the dataset in the exact same way each ...
user avatar
0 votes
0 answers
18 views

Difference between C-Index and Spearman correlation

Suppose I have a list that reflects the priority of web pages for recrawling: l1 = [3, 2, 1, 4, 2, 5] Now, I have tried to estimate the priorities with two ...
user avatar
0 votes
0 answers
7 views

Are goal-reaching and optimizing the utility function special cases of performance measure?

In َArtificial Intelligence: A Modern Approach by Russell, performance measure is defined as something evaluating the behavior of the agent in an environment. Rational agents are defined as agents ...
user avatar
  • 377
0 votes
0 answers
18 views

Simple formula comprehension: help medical worker who are struggling to understand AI

https://www.nature.com/articles/s41467-020-17419-7 I am a medical school graduate and I really want to learn AI/ML for computer-aided diagnosis. I was building a symptom checker and I found the ...
user avatar
  • 101
0 votes
0 answers
12 views

Is there any other type of network architecture difference?

I'm learning a bit about network architecture.I wonder if there are other types of network architecture besides a perceptron and simple multi-layer networks? And two popular applications of its
user avatar
  • 1
1 vote
0 answers
56 views

Could someone explain the algorithm from this paper? (Thank you) [closed]

Trying to get a fair understanding of our artificial immune systems. To do this I’ve been reviewing this paper, but the algorithm and mathematics is over my head, could someone explain the below to me ...
user avatar
  • 11
1 vote
1 answer
56 views

Is an AI upscaler incapable of reducing entropy?

I was reading the description of Anime4K (a video upscaler software) and I found a statement triggering my attention: [upscaling is done] without any meaningful decrease in entropy (lost information ...
user avatar
  • 113
0 votes
0 answers
24 views

Using Restricted Boltzmann Machines for clustering data

I want to use RBMs as a clustering model and the idea is to use an RBM for clustering a 16 class clustering problem with 4 nodes in the hidden layer. The clustering is done by updating the hidden ...
user avatar
1 vote
0 answers
38 views

What is the difference between Swarm intelligence and Multiagentsystems?

Swarm intelligence and Multiagent systems are both a part of Distributed AI. Multiagent systems describe a system with agents, which communicate with each other. Swarm intelligence describes systems, ...
user avatar
  • 111
1 vote
0 answers
26 views

Applications of derivative only, zeroth-order free optimization

I understand what is derivative-free optimization, and I am thinking a similar problem where the function $f$ we are optimizing is unknown and the only information we can acquire is the derivative. In ...
user avatar
  • 65
0 votes
1 answer
25 views

What is the relation between the compatibile features and the state features in Actor Critic Algorithm?

According to Actor-Critic algorithm, $\psi_{\theta}=\nabla_{\theta}\ln \mu_{\theta}(s, a)$ where $\mu_{\theta}(s, a)$ is the policy followed by the actor and $\psi_\theta$ is the compatibile features ...
user avatar
2 votes
1 answer
124 views

How to transform an Abstract Syntax Tree (AST) to an Abstract Binding Tree (ABT)? (for machine learning fo theorem proving)

I was reading the HOList paper that applies Graph Neural Networks (GNNs) to the HOL Light (HOList) data set and benchmark for ML for theorem proving. They describe their results etc but there is no ...
user avatar
0 votes
1 answer
30 views

What does "satisfactory definition" mean?

I am reading the book Artificial Intelligence (A modern approach) by Stuart Russell and Peter Norvig. While reading the book, I saw the below sentence in the book. The Turing Test, proposed by Alan ...
user avatar
-1 votes
1 answer
22 views

A very simple question about Admissible Heurisitcs

Given admissible heuristics f(s), g(s), h(s). It is true that max(f(s), g(s), h(s)) is still admissible.. but is it still admissible if its max(f(s), g(s) + h(s)). I believe it is not admissible but I ...
user avatar
  • 1
-1 votes
1 answer
88 views

UCS and Dijkstra's algorithm do both of them give the minimal cost between two vertices?

i tried both algorithm to find the shortest path with minimal cost between two vertices,but most of the time Dijkstra gives a different path and the cost is smaller than the cost for the path UCS ...
user avatar
1 vote
0 answers
50 views

Necessary or useful models/techniques for simulating natural evolution?

I'm a Psychology student with a decent (yet not extensive) knowledge of mathematics and computer science. My knowledge on this two fields are those of a person beginning the third year of computer ...
user avatar
  • 111
1 vote
1 answer
25 views

I'm quite confused about the convergence of pix2pix cGAN, how can we tell whether my model is well trained?

Usually we will see decreasing loss for regular CNN model, but for GAN, it seems to be not that simple. How can we tell whether my model is well trained?
user avatar
0 votes
0 answers
63 views

How to modify the following Dijkstra/ Uniform-cost search to return the result for all end points?

I know there is a lot of code out there that does this, but in particular, I'm trying to modify the following code to not just return the goal node/ one end point, but all endpoints. How do I go about ...
user avatar
2 votes
1 answer
36 views

Raising to the T in machine learning

What does it mean when in a machine learning paper there is $(arg)^{T}$, what does the T does to an arg in this 3b1b video on neural networks he puts the: $(w^{l-1})^{T}$
user avatar
  • 21
1 vote
1 answer
29 views

Artificial Intelligence: theory vs processing power

It is common to see articles praising the advances in AI (here is one example). There is no doubt that significant progress has occurred on all kinds of automation, hard games like chess, etc. The ...
user avatar
1 vote
1 answer
70 views

Could AI be used to detect when a human is picking survey response options randomly?

Context: I am a clinical psych researcher dabbling in machine learning. Humans cannot be truly random. Therefore, could machine learning be used to analyze a string of numbers and determine the ...
user avatar
  • 11
0 votes
0 answers
17 views

Different types of interpolation used in computer vision

Known codition: four pixels shown in the image $(i,j),(i+1,j),(i,j+1)$ and $(i+1,j+1)$ $a=0.9$ and $b=0.4$ I was able to calculate the bilinear interpolation using the algorithm provided by https://...
user avatar
1 vote
0 answers
39 views

Proving facts in inverse reinforcement learning [closed]

I was going through paper titled "Algorithms for Inverse Reinforcement Learning" by Andrew Ng and Russell. It states following basics: MDP $M$ is a tuple $(S,A,\{P_{sa}\},\gamma,R)$, where ...
user avatar
  • 215
0 votes
0 answers
29 views

Will we be able to « see » COVID (or any other viruses) in our environment in the future?

Given that cameras, computer vision and AI are constantly evolving with greater zoom, macro, processing power... is it possible that some day cameras would be able to « scan » a room and detect COVID (...
user avatar
  • 418
0 votes
1 answer
38 views

Converting into CNF

I am still a bit confused by how to convert into CNF even though I have the rules written down. How do I convert the following sentence into CNF? $(I \lor M) \Rightarrow H$ I know I need to get rid of ...
user avatar
  • 83
0 votes
1 answer
24 views

Is any of the assumptions hold true for the mentioned?

Suppose the use of linear regression. The result of the MSE is 120.5(mean squared error) for the train-set. Wev'e reached the minimum of training the data. Is it possible that by applying Lasso(L1 ...
user avatar
0 votes
1 answer
30 views

Is it possible to do face recognition with just the eyes?

Assuming the input photo is focused on a person's face, if the person is wearing a surgical mask, most face recognition software fail to identify the subject's face. Most facial landmark models are ...
user avatar
  • 1
1 vote
0 answers
33 views

Intelligent task distributor

On a distributed system, there are more than 50 machines than continuously read from a database which tasks they have to process. There is no criteria based on which a certain machine chooses which ...
user avatar
  • 111
1 vote
0 answers
52 views

Reinforcement learning and Graph Neural Networks: Issue with entropy [closed]

I am currently working on an experiment to link reinforcement learning with graph neural networks. This is my architecture: Feature Extraction with GCN: there is a fully meshed topology with ...
user avatar
1 vote
1 answer
47 views

Is transfer learning applied on only similar datasets only?

I am trying to make a CNN model on different brands of logos . Firstly , I wrote a CNN from scratch and trained it on which I got 70% accuracy, I have total 40 classes and each class has 100 images . ...
user avatar
  • 131
1 vote
1 answer
241 views

How does node expansion work in a graph for AI search?

I want to try and write an example that solves the problem of travelling from one location to another described in the book AI: A modern approach. The problem involves getting from a particular city ...
user avatar
  • 83

1
2 3 4 5
11