Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [algorithm]

For questions about algorithm's that exhibit characteristics of intelligence, or are critical components in systems that exhibit intelligence, and problem-solving and goal-based algorithms in general.

1
vote
0answers
14 views

Why does Q-learning converges to optimal policy even if I am acting suboptimally?

In Q-learning, during training, it doesn’t matter how I select actions. The algorithm always converges to optimal optimal policy. Why does this happen?
1
vote
0answers
15 views

What Actually is Off-Policy Q-Learning?

Recently I have come across an information stating: Q-learning converges to optimal policy -- even if you’re acting suboptimally! It also states: When an optimal policy is still learned from ...
2
votes
1answer
23 views

What is the time complexity of the value iteration algorithm?

Recently, I have come across the information that the time complexity for each iteration of the value iteration algorithm is $\mathcal{O}(|S|^{2}|A|)$, where $|S|$ is the number of states and $|A|$ ...
0
votes
1answer
17 views

Breadth first search VS recursive best first search?

What is the difference between breadth first search and recursive best first search ? How can I describe the key difference between them?
3
votes
2answers
60 views

What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function ?...
-2
votes
0answers
31 views

Limitation of “Simulated annealing” algorithm

What are the limitations of the Simulated Annealing algorithm and how can one overcome these limitations.
6
votes
2answers
1k views

What are the limitations of the hill climbing algorithm and how to overcome them?

What are the limitations of the hill climbing algorithm? How can we overcome these limitations?
1
vote
1answer
47 views

How is simulated annealing better than hill climbing methods?

In hill climbing methods, at each step, the current solution is replaced with the best neighbour (that is, the neighbour with highest/smallest value). In simulated annealing, "downhills" moves are ...
1
vote
0answers
49 views

Nature-inspired artificial intelligent methods for Blockchain?

I am working on the blockchain technology and I am not very familiar with the AI concept. The proposal of this web page: (http://www.euraxess.lu/jobs/349354) opens a discussion about use of nature ...
0
votes
1answer
24 views

How does the internal convolution Neural Network work?

I found the below image of how a CNN works but I don't really understand it. I do understand CNNs (I think) but I find this diagram very confusing. My summarized, simplified understanding : -...
1
vote
0answers
26 views

What is the difference between IDS* and A* Algorithm?

What is the difference between IDS* and A* Algorithm. And how IDS* is better than A* Algorithm. Please explain your answer with pros and cons. Thanks
1
vote
0answers
26 views

What are the differences between uniform-cost search and greedy best-first search?

What are the differences between the uniform-cost search (UCS) and greedy best-first search (GBFS) algorithms? How would you convert a UCS into a GBFS?
1
vote
1answer
52 views

Weighted move rating for AI

My AI (for the card game schnapsen) currently calculates every possible way the game could end and then evaluates the percentage of winning for every playable card / move. The calculation is done ...
2
votes
1answer
89 views

What are the practical differences between A* and greedy best-first search?

What are the differences between the A* algorithm and the greedy best-first search algorithm? Which one should I use? Which algorithm is the better one, and why?
-1
votes
0answers
31 views

How IDS* is better than A* algorithm? [closed]

A* has consistency,monotinicity and triangle inequality while IDS* have different properties so which algorithm is better to find out the shortest path to solve the problems
0
votes
1answer
22 views

How the number of trees to be generated in Random Forest algorithm?

The default number of trees to be generated is 10. But I thought it should be a very large number and I put 500 trees. However it performed better when the number of trees are 10 than 500. My question ...
0
votes
0answers
49 views

How does the recursive best-first search algorithm work?

I am student of MCS and my teacher suggest us to read this topic by self and i search about and i solve its map mean graph but am confused in how its pseudo work and where its use. My question is ...
2
votes
1answer
39 views

Which algorithm is used in robot Sophia to understand and answers the questions?

Which algorithm is used in robot Sophia to understand and answer the questions ?
1
vote
1answer
43 views

Which Algorithm is best for Robots?

I am a student and I study Algorithms like tree search algorithm graph search algorithm Then apply BFS DFS UCS IDS DLS Where are all these algorithms are used? I know there is a long list of ...
3
votes
2answers
128 views

How does the uniform-cost search algorithm work?

What is the uniform-cost search algorithm? How does it work? I would appreciate to see a graphical execution of the algorithm. How does the "frontier" evolve in the case of UCS?
1
vote
0answers
24 views

When should the iterative deepening search and the depth-limited search be used?

When should the iterative deepening search (IDS), also called iterative deepening depth-first search (IDDFS), and the depth-limited search be used?
0
votes
2answers
75 views

Greedy best first Search Algorithm vs A* search Algorithm

Greedy best first search Algorithm take the history and then check value ans then reach to goal. In A* search Algorithm take history and also cost then calculate value then reach to goal. When we ...
1
vote
1answer
55 views

Question in NLP

I'm working on a project,whereby; one of the actors is "Teacher" and it's role will be, insert the course name, outcomes of skills, then insert the question, student degree and automatically will be ...
0
votes
0answers
22 views

How to apply iterative deepening on graph?

I have learned that iterative deepening works like this : But I find it difficult to apply. I have a search problem of Romanian map and I have to find a goal through iterative deepening. And tried ...
5
votes
1answer
62 views

what other computer science algorithms could use tensor specific hardware?

It seems like only neural networks need tensor hardware? Are there any other artificial intelligence algorithms that could benefit from many tensor calculations in parallel? Are there any other ...
4
votes
1answer
70 views

Algorithms for games with very high branching factors (Connect6)

Connect6 is an example of a game with a very high branching factor. It is about 45 thousand, dwarfing even the impressive Go. What algorithms can you use on games with such high branching factors? I ...
3
votes
1answer
88 views

Monte Carlo Tree Search Expansion Phase

I'm confused regarding a specific detail of MCTS. To illustrate my question, lets take the simple example of tic-tac-toe. After the selection phase, when a leaf node is reached, the tree is expanded ...
4
votes
1answer
90 views

TRPO/PPO importance sampling term in loss function

In the Trust-Region Policy Optimisation (TRPO) algorithm (and subsequently in PPO also), I do not understand the motivation behind replacing the log probability term from standard policy gradients ...
5
votes
2answers
386 views

Why does the discount rate (γ) in the Monte-Carlo Policy-Gradient Method (episodic) appears twice?

I was reading the book Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto (complete draft, November 5, 2017). On page 271, the pseudo-code for the episodic Monte-Carlo ...
3
votes
2answers
69 views

Are there any discount-factors based on branching factors?

I recently came across this function: $$\sum_{t = 0}^{\infty} \gamma^t R_t.$$ It's elegant and looks to be useful in the type of deterministic, perfect-information, finite models I'm working with. ...
6
votes
7answers
1k views

Keeping track of visited states in Breadth-first Search

So I was trying to implement BFS on a Sliding Blocks puzzle (number type). Now the main thing I noticed that is if you have a 4*4 board the number of states can be ...
4
votes
1answer
84 views

Algorithm For Making Balanced Weapons In A Game?

I am trying to make balanced weapon pairs. So there are five stats per weapon, and I am simulating a number of combats (1000) with different stats randomized, and counting the win, lose, and draw of ...
2
votes
1answer
25 views

What's an appropriate algorithm for classification with categorical features?

My input data consists of a series of 8 integers. Each integer is a discrete token, rather than a relative numeric value (i.e. '1' and '2' are as distinct as are '1' and '100'). The output is a ...
7
votes
3answers
186 views

Mathematics for AI researcher

What are the mathematical prerequisites for understanding the core part of the algorithms in artificial intelligence and developing own algorithm? Please refer me the specific books.
1
vote
0answers
22 views

Simple question about HS algorithm's formul(Optical flow)

In the below pic, I can not understand what U vector is? It says flow field but I can not imagie what really is the flow field?
2
votes
3answers
105 views

What is a “generalized” machine learning algorithm?

What does it mean when it is said that Machine Learning algorithm results can be "generalized"? I don't understand what "generalized" algorithms, routines or functions are. I have searched ...
0
votes
0answers
20 views

A question about visualizing “Lucas-Kanade(optical flow)” algorithm

I am reading O'Reilly's OpenCV 3 book. In keypoints section(for tracking objects), there is an algorithm named "Lucas-Kanade". in the below image it tries to give a visualization of it but I can not ...
6
votes
3answers
78 views

Detect visual attention area in an image

I'm trying to detect the visual attention area in a given image and crop the image into that area. For instance, given an image of any size and a rectangle of say LxW dimension as an input, I would ...
0
votes
1answer
37 views

Number of node expansions performed by Breadth first search

an agent aims to find a path on a hexagonal map with initial state s0 in the center and goal state s⋆ at the bottom as depicted below. The map is parametrized by the distance n ≥ 1 from s0 to any of ...
4
votes
0answers
47 views

Relative compute time for each type of layer in a neural network

Hello, I would like to know whether this picture from the paper: Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability valid? Questions: 1) Does ...
6
votes
3answers
92 views

How to use computer vision to find corners of a soccer field based on location coordinates?

I want to use computer vision to allow my robot to detect the corners of a soccer field based on its current position. Matlab has a detectHarrisFeatures feature, but I believe it is only for 2D ...
1
vote
1answer
54 views

Given a query image Q and two other images X and Y, how to determine which one is most similar to Q?

Given a query image Q and two other images X and Y (you can assume they have more or less the same resolutions if that simplifies the problem), which algorithm would perform extremely well at ...
1
vote
1answer
61 views

Which machine learning algorithm is suitable for detecting text w.r.t set of words

Considering the scenario where supervised training data-set in the form of sentence will be given to train the machine The Bomb which had been planted by Terrorist on this morning was defused by ...
1
vote
1answer
92 views

LinUCB with Hybrid Linear Models

In Li et al. (2010)'s highly cited paper, they talk about LinUCB with hybrid linear models in Section 3.2. They motivate this by saying, "In many applications including ours, it is helpful to use ...
1
vote
1answer
96 views

How to add contextual follow up like Google Assistant

I am developing PDA like Google assistant on Android. So far, so good. But now, I want to add contextual follow up like Google assistant so it can keep the train of thought. As demonstrated here- ...
1
vote
0answers
28 views

The algorithms to get most with reasonable efforts and time

Suppose that there are six type of problems to be handled when reading a book, I elaborate it as follow: ...
0
votes
0answers
16 views

What is the most efficient and flexible algorithm to find constant term in a function

Suppose we have a discrete function which domain and codomain are both integers. For example, that function could be a signal from an ADC. In my case it is digitized signal from photomultiplier (see ...
4
votes
3answers
162 views

Definitive methods vs Neural Networks and Artificial Intelligence

So I came across these 2 questions: Ideas on how to make a neural net learn how to split sequence into sub sequences Search minimum value with learning machine algorithm For me both problems could ...
3
votes
5answers
133 views

Ideas on how to make a neural net learn how to split sequence into sub sequences

How can I train a neural network to recognize sub-sequences in a sequence flow? For example: Given the sequence 111100002222 as an input sample from a stream, the neural network would recognize that ...
3
votes
1answer
207 views

Q Learning and State(Stochastic Environment)

I am currently building my first AI in a stochastic environment and the following question came to my mind. The Q function uses the states(current and future)to determine the action that gets the ...