Artificial intelligence Reducing the number of markov-states in reinforcement learning

I've started toying with reinforcement learning (using the Sutton book). I fail to fully understand is the paradox between having to reduce the markov state space while on the other hand not making assumptions about what's important and what's not. background Eg. the checkers example, Sutton says that one should not assign rewards to certain actions in the game, such as defeating an opponents piece. He claims this may optimize the AI for taking pieces not win the game. Thus, rewards should onl

Artificial intelligence tangible intelligence

I am afraid this question is not supposed to be asked here but I have spent lots of time over google and didn't find anything fruitful so just need to know from here if anyone can help me in finding this thing. some search phrase that could help or some website. I want to know if Intelligence is tangible or not? I think it is and Artificial Intelligence is an example but, I need to get some examples or reason for it that am unable to find. looking for some website links or a phrase to search ov

Artificial intelligence per-requisites listed against each of the A.I. field

Yes A.I. field is very vast field. I have gone through the wiki page of A.I. and read about the different fields of it. I think any enthusiastic beginner can choose one of those fields based on his/her interest to get into A.I. But before getting in it is always good to have the per-requisites of the appropriate field. It is very useful to have those per-requisites listed against each of the A.I. field to any beginner of A.I (like me) so that he can refresh his knowledge in them once and get s

Artificial intelligence Unity 2D/3D - Making a computer opponent (AI) for a match-3 game

I'm looking for guidance/advice on where to start to create a computer AI opponent for a match-3 game. This issue has been stumping me for years (literally), as I've not been able to figure it out. I've exhausted Google in finding this answer. Sample match-3 games that have a computer opponent include: Puzzle Quest and Crystal Battle. What programming methodologies are used in creating an AI opponent like this, and how can I apply it to Unity 2D scripting? Where/how can I start? I am mainly lo

Artificial intelligence Luis Training and associating it with intents

Currently, I have a few intents, one of which is "Greeting", and I have "good morning" trained to fire that intent. However, "Sunday morning, "Monday morning", etc... always fire this intent, incorrectly. I have spent the morning training "{Datetime} morning" to associate with the other intent, however, it is not learning. Is there a better method, or do i have just to spend more time, typing the same intent over and over again to make LUIS associate it with the other intent?

Artificial intelligence Classifier algorithms that can be trained with only "good" data

I'm trying to find a suitable classifier to work for my application. I really like Support Vector Machines for this, but I've come across a problem with my input data. The user trains the classifier using real-world recorded audio. There are only two classes - 'Good' and 'Bad'. My issue is that almost all of the training data will be 'good' - it's very unlikely to encounter 'bad' information during an on-site training run. Is there an algorithm that works like an SVM, but returns a result of

Artificial intelligence Designing bayesian networks

I have a basic question about Bayesian networks. Let's assume we have an engine, that with 1/3 probability can stop working. I'll call this variable ENGINE. If it stops working, then your car doesn't work. If the engine is working, then your car will work 99% of the time. I'll call this one CAR. Now, if your car is old(OLD), instead of not working 1/3 of the time, your engine will stop working 1/2 of the time. I'm being asked to first design the network and then assign all the conditional pr

Artificial intelligence Neural Network Recommendation Engine

How would one design a neural network for the purpose of a recommendation engine. I assume each user would require their own network, but how would you design the inputs and the outputs for recommending an item in a database. Are there any good tutorials or something? Edit: I was more thinking how one would design a network. As in how many input neurons and how the output neurons point to a record in a database. Would you have say 6 output neurons, convert it to an integer (which would be anyth

Artificial intelligence Actions and effect axioms

I want to create an axiom-action tha will enable an agent to move up or down between doors if the robot is in a lift node, and if a route connects the two lift nodes A map which shows the structure of the building. Each node either represent a room (Rn) or a lift (Ln). The robot can either move between rooms (solid lines), or move between oors (dashed lines). The robots needs to specify the direction (up/down) when taking the lift. I was thinking of something like: isRo

Artificial intelligence Utilitarian vs. Egalitarian Allocation in Game Theory in AI

Let's say I have two players: Player A and Player B and they have preferences over what resources (let's just be general and use the term 'resource'). Their preferences could be: {p} {q} {p,q} {} A 10 15 20 0 B 5 5 10 1 This says that the two players can have one resource, both or none. The greater the number the more the player wants it. I believe the 'utilitarian' view would be to maximise the allocation overall so this would

Artificial intelligence How do we Initialize a Hopfield Neural Network?

I have just started reading about neural networks and I have a basic question. Regarding "initializing" the Hopfield network, I am unable to understand that notion of initialization. That is, do we input some random numbers? or do input a well defined pattern which makes the neurons settle down first time up, assuming all neurons were at state equal to zero, with other stable states being either 1 or -1 after the input. Consider the neural network below. Which I have taken from HeatonResearch

Artificial intelligence Decision Tree. Strategy for noise

What are the good strategies to combat noise in decision tree? In my training data, I have two records with the same attributes but they give different classification. Female, Luxury, LV, Yes Female, Luxury, LV, No Based on my reading, it says to return the plurality classification of these two records. But that will raise a problem when i want to make a prediction because the output of my prediction should be either yes or no. So, trying to find out what are the strategies I can use in

Artificial intelligence nominal value not declared in header

I'm generating a arff file with groovy from a xslx, but when i try to open this file in weka i got this error: File "..." not recognised as an 'Arff data files' file. Reason: nominal value not declared in header, read Token[Ativo], line 16 i can't understand why i'm getting this error can someone helpme to fix this error, and explain why it's happening? Generated file @relation kd-itempedido @attribute tipopedido {Assistencia,Recompra,Venda,Troca} @attribute aprovado {0.0,1.0} @attr

Artificial intelligence Watson Conversation: What is lost when restoring a Workspace from a JSON "dump"-file?

What is "lost" or what kind of measurable impact has it, when restoring a previously heavily trained Watson Conversation Workspace from its JSON dump-file? As it seems to me on a small example workspace, the bot is running again. Most probably not as good as before. Considering a much larger workspace in the future: Is there a way to quantify and/or measure such lost quality? to "retrain" the bot (restore the original bot quality after restoring a trained workspace from its dump)? And wh

Artificial intelligence Policy Gradient: Initialization of Policy Parameter Problem

I have some problems with initializing the Policy Parameter Theta for the REINFORCE algorithm from the book: Reinforcement Learning: An Introduction, 2nd Edition, Chapter 12, Sutton & Barto Here is the pseudo code for the algorithm: They say you can initialize Thetas(Policy Parameter) with arbitrary values, e.g. 0. But then I get completely wrong results: To fix this I had to initialize them in such a way so they correspond to an Epsilon-Greedy policy. This can be achieved by taking i

Artificial intelligence What would be a good AI strategy to play Gomoku?

I'm writing a game that's a variant of Gomoku. Basically a tic tac toe on a huge board. Wondering if anyone knows a good AI strategy for the game. My current implementation is very stupid and takes a long time (O(n^3), approx 1-2 second to make a move): -(void) moveAI { //check if the enemy is trying to make a line horizontally, vertically, or diagonally //O(n^3 * 3) [self checkEnemies]; //check if we can make a line horizontally, vertically, or diagonally //O(n^3 * 3) [

Artificial intelligence How do I define a fitness function?

I'm working on a project which will have a selected set of data and each data will have different attributes. I will need to use a fitness function to choose the data that best matches my selected scenario using the attributes. However, I don't really find any sites explaining how to define my own fitness function. All I've got is that it's part of genetic algorithm, and this is as far as I got. So, can I be given some pointers here?

Artificial intelligence How to infer correctly?

How do AI based agents infer a decision that are not necessary rational but logical correct based on previous experience. In the field of AI how do experts system infer, what kind of maths and probabilities are involved here? I plan on creating an intelligent, but don't no where to start. Pointers or links to any resources would be grateful. Preferably a resources that describes the mathematical concept for those whom are not mathematical minded.

Artificial intelligence Can we programmatically determine the components of a website by crawling its content?

Can we programmatically determine the components of a website by crawling its content? I understand that this seems kind-of impossible but i think anything is possible in code. I am trying brainstorm ideas based on which i could determine the individual components of a website if i have crawled all of its data! I am interested in determining components such as , for example , in case of a ecommerce website, i would want to determine or identify: 1. Login Url 2. Registration Url 3. Dashboard ur

Artificial intelligence cross and nought game and find the heuristic function

I have the artificial intelligence course this semester and I have to hand in an AI project... since I do not have any good idea for project that I want to choose I decided to use the simplest one for practice to get a more solid idea: cross and nought game But even in this game I need a heuristic function to estimate each game branch for example if I have that function it is easy to estimate the best next move but now the problem is how can I find that function?(I need an indication to find

Artificial intelligence Sigmoid for regression

i just started with data-science, so if this is a very dumb question then please excuse me... So, i just learnt about the sigmoid neuron, and learnt that its range is [0, 1]. The question i have is that how can it be used in regression tasks, for example to predict the cost of any real estate property, or the imdb rating of a movie, or something I am aware of the scaling method (multiplying the output of sigmoid with any number) to get real outputs, but that works only for outputs which have an

Artificial intelligence Less Mathematical Approaches to Machine Learning?

Out of curiosity, I've been reading up a bit on the field of Machine Learning, and I'm surprised at the amount of computation and mathematics involved. One book I'm reading through uses advanced concepts such as Ring Theory and PDEs (note: the only thing I know about PDEs is that they use that funny looking character). This strikes me as odd considering that mathematics itself is a hard thing to "learn." Are there any branches of Machine Learning that use different approaches? I would think

Artificial intelligence Association Rule Mining on a FOAF dataset of social networks

I am working on a project called "association rule discovery from social network data: Introducing Data Mining to the Semantic Web". Can anyone suggest a good source for an algorithm (and its code. I heard that it can be implemented using Perl and also R packages) to find association rules from a social network database? The snapshot of the database can be got in the following link:

Artificial intelligence Supervised learning with multiple sources of training data

I'm not sure it's the right exchange site for machine learning questions but I did see ML questions before so I'm trying my luck (also posted at I have training instances that come from different sources so building one model doesn't work well. Is there a known method to use in such cases? Example explains best. Let's say I want to classify cancer/non-cancer given training data that was constructed based on different populations. Training instances from one popu

Artificial intelligence Difference between Neural Network and Evolutionary algorithm

I have a good basis on Evolutionary Algorithms, so now i started to read about Artificial Neural Networks. I come across this tutorial on, showing how to use a ANN to evolve Tanks that collect mines. It uses a GA to evolve the input weights on each Neuron. I know i could use GA (without the ANN) to solve the same problem. I already created a Tetris Bot using only GA to optimize the weights in the grid evaluation function (check my blog http://w

Artificial intelligence Weighting the heuristic function in A*

Three AI newbie question: Why should a heuristic be admissible for A* to find an optimal path? What good is a tie braking technique if obstacles are in the way? What algorithm is good for finding a path on a grid with obstacles? (like pacman) For the first question Lets take as a base the Manhattan distance heuristic, and call is h(x). Now why should A* find a non-optimal path with a new heuristic that is 8*h(x) + 5? (random numbers). As far as I understand in A* algorithm, the decision will

Artificial intelligence Interpretation of my neural network output

I am using a NN with activation function: F = 1 / ( 1 + e^(-4.9*S) ) S is the sum of inputs the network has 1 output node and is interpreted as states of a motor the motor has 3 states: 1-clockwise motion 2-counterclockwise motion 3-locked the question is how should i interpret the output? is it correct to say for example: if ( output > 0.8 ) then clockwise motion if ( 0.2 > output < 0.8 ) then locked if ( output < 0.2 ) then counterclockwise motion i mean is it correct to interpr

Artificial intelligence Research on machine vision and game solvers

I am currently creating an intelligent agent for a game solver. This system will be hosted in a computer different from the host of the game which it will play. Hence, I am looking for similar researches or projects that uses machine vision for a game solver. The game is a board game/involving tiles, by the way. These are the things I think I need to do: Edge detection Pattern recognition Board/tile detection similar to that is being used to detecting chess boards I really cannot find somet

Artificial intelligence Keywords recognition - Is it possible?

I have a system that offers a user to search for whatever he wants, and grabbing the content from different places into one page. I restrict the search results by a keyword/label or a few keywords, so the user won't get junk he never asked for. And I always stick to the main market/label theme(keyword) not to let the search go wrong. At the beginning all was fine, but then, when I went deeply into developing this system, I started to understand that I cannot predict or filter the content that

Artificial intelligence Solving a puzzle game using AI

I have made a puzzle where the player slides blocks around to goals - the rules are fairly simple: Only one slider block may move at a time The object is to move the slider blocks into goal nodes - you only need to fill the goal nodes, not necessarily get all slider blocks into the goal nodes. If the slider block slides on ice, it will continue moving in that direction until it is stopped or moved If the slider block hits something solid (concrete, another block) it stops and can be moved agai

Artificial intelligence Bug in Resilient Backpropagation?

I'm struggling with implementing Resilient Propagation correctly. I already implemented the backpropagation Algorithm to train a Neural Network, and it works as expected for an XOR-Net, i.e. it takes about 600 Epochs to drop Error below 1%. Now i tried implementing Resilient Propagation ( for the same problem and for the first few Epochs Error drops quickly to 23% but then raises to 50% and stays there. I implemented it exactly as per description in http://www

Artificial intelligence Dynamic content for webpage

a couple weeks ago, I had that idea of creating a "smart content element" for my CMS. The idea behind that is, based on the visited pages of a visitor (saved eg. in a cookie), the visitor gets dynamic content. Eg. I visit some product pages and after 2 pages, the cms shows on another product page with normal content and one dynamic content element, based on suggested content. Of cource the user flow behind that needs to be really good and approved. Is that some how possible, or my does someth

Artificial intelligence Can a cache be used for an alpha-beta search algorithm?

I'm working on a minimax tic-tac-toe algorithm. I got it working fine, caching each state in the tree. Then I implemented alpha-beta pruning, which seemed to affect the game. I think the problem is that nodes cannot be "trusted" if any of their descendants (children, grandchildren, etc.) were pruned. Is this true? For now, I'm only caching states if they don't have pruned descendants. This image shows my point (not tic tac toe). The max player is the upwards triangle, which should choose the m

Artificial intelligence Artificial Intelligence In Ethereum Smart Contracts

I have been working with Ethereum smart contracts for a while for DAPP developments, recently i grew interest in working with Smart Contracts for Artificial intelligence. I found some work on net but it is not completely relevant to my idea. I actually want to have AI technique coded inside smart contract and perform prediction. I know that running AI inside smart contract would cost a ton but i would like to explore the field. I am still wondering why there has been very less work done in this

Artificial intelligence Connect 4 with neural network: evaluation of draft + further steps

I would like to build a Connect 4 engine which works using an artificial neural network - just because I'm fascinated by ANNs. I'be created the following draft of the ANN structure. Would it work? And are these connections right (even the cross ones)? Could you help me to draft up an UML class diagram for this ANN? I want to give the board representation to the ANN as its input. And the output should be the move to chose. The learning should later be done using reinforcement learning and t

Artificial intelligence Which activation function should I use for this Neural Network?

We are developing a neural network for Checkers game. In our training data, 0 represents blank cell, 1 represents white piece, -1 represents white king, 2 represents black piece and -2 represents black king So, what we need is an activation function withing range [-2, 2]. Which activation function should we use? Please give your suggestions regarding this.

Artificial intelligence How to apply reinforcement learning?

I understand it in concept. You have an agent and an environment. And then you have a set of states, which each have a value. The agent then either choses to "explore" or "exploit" and modifies it's knowledge according to what happened. My problem is that I can't seem to figure out how to actually apply it to code or to any actual problem. Everytime I look it up, I just end up getting the same few equations with no explanation on how to use them. I'm trying to write a RL agent for tetris, and

Artificial intelligence Can pruning be implemented in the expectiminimax algorithm?

I'm current using the expectiminimax algorithm, which is working great in my current situation: max -> min -> chance -> max -> min -> chance -> (repeat) I cannot in any way do max/min -> Chance -> (repeat) due to way the game works. I feel as though the alpha is going to be inaccurate if I proceed to convert my algorithm over. Is there any side effects to implementing pruning (apart from the horizon effect) with my current set up or am I just overthinking this?

  1    2   3   4   5   6  ... 下一页 共 6 页