Questions tagged [ai-design]

For questions related to the design of AI agents, algorithms or models.

Filter by
Sorted by
Tagged with
0
votes
1answer
161 views

What is the best neural network architecture for this problem?

I built a three-layer neural network (first is 1D convolutional and the remaining two are linear). It takes an input of 5 angles in radians, and outputs two numbers from 0 to 1, which are respectively ...
3
votes
0answers
220 views

What is the state of the art AI training technique for imperfect information 2 player turn based games?

As far as I can tell (correct me if I'm wrong), Alphazero (with MCTS and neural network heuristic function RL) is the state of the art training method for turn based, deterministic, perfect ...
5
votes
1answer
163 views

How would one implement a multi-agent environment with asynchronous action and rewards per agent?

In a single agent environment, the agent takes an action, then observes the next state and reward: ...
0
votes
1answer
39 views

How would an AI understand grids?

OK, now I think an AI must view grids in a different way to computers. For example a computer would represent a grid like this: ...
3
votes
1answer
30 views

Image classification with an associated matrix

I have a dataset of images with 9 different classes. However, there are different categories with the same type of associated image and only can be differentiated with an associated matrix in my ...
4
votes
2answers
259 views

AI on Academic vs Industry vs Competition

When we are working on an AI project, does the background or the domain make the process different? The "domain" I mean here is like AI for academic research, AI for industry, and AI for competition. ...
3
votes
1answer
73 views

How to handle multiple types of decisions?

In lots of games there are multiple phases or decision points that are not similar yet seem to have a dependency on one another when taking the perspective of the overall strategy of the player. A ...
1
vote
0answers
26 views

AlphaZero value at root node not being affected by training

I have written my own AlphaZero implementation and started training it recently. Problem is, I am 99% sure there is a mistake and I do not know how to tackle this, since I cannot explain it. I am new ...
2
votes
1answer
73 views

Which predictive algorithm is most appropriate for a proceeding situation?

I'm new to artificial intelligence. I am looking for the most appropriate AI solution for my application, which is developing an algorithm to predict a proceeding situation (edited: I want my ...
5
votes
3answers
60 views

What should we do when we have equal observations with different labels?

Suppose we have a labeled data set with columns $A$, $B$, and $C$ and a binary outcome variable $X$. Suppose we have rows as follows: ...
2
votes
1answer
35 views

How to select the most appropriate set of actions for a given environment or task?

Given a robot in a situation such as in a library reading a book. Now I want to create a neural network that suggests an appropriate action in this situation. And, generally, ignore actions such as "...
2
votes
3answers
228 views

One vs multiple output neurons

Consider an MLP that outputs an integer 'rating' of 0 to 4. Would it be correct to say this could be modeled in either of the following ways: map each rating in the dataset to a 'normalized set' ...
3
votes
1answer
187 views

Can AI be used to reverse engineer a black box?

A while back I posted on the Reverse Engineering site about an audio DSP system whose designer had passed away and whose manufacturer no longer had source code (but the question was deleted). ...
1
vote
1answer
36 views

Excel in multiple formats

I want to use AI to extract data from spreadsheets in different format. Example ...
2
votes
0answers
22 views

A NN based model of a Cattle for 'Heat Detection'

I am very new to AI/ML but have lot of interest in these. I am trying to understand how this gadget works. So far I have understood that a NN model of the cattle is generated by offline ...
1
vote
0answers
16 views

A gated neural network for internal thought?

I have an idea for an RNN which has no separate internal memory state only an output. But there is a gate in which tells the neural network whether the output will be acted out in the physical world ...
1
vote
1answer
103 views

Create an AI to solve a puzzle (by deduction)

Some puzzle games have a unique solution that can be solved by deduction rather than guesswork (e.g. Slitherlink, Masyu). Using a computer to solve this puzzle it's pretty easy, we can use a ...
4
votes
2answers
48 views

What kind of output should be used for predicting angles in DNNs?

I am building a model which predicts angles as output. What are the different kinds of outputs that can be used to predict angles? For example, output the angle in radians cyclic nature of the ...
1
vote
1answer
356 views

How to estimate the cost and time to complete an AI Project [closed]

If you are a freelancer, when a client asks to create a website we can easily measure how much the total cost is needed based on the requirements of the client. (the backend, UI/UX design, features, ...
1
vote
0answers
317 views

AI for Selenium Test Automation

I am seeking help to implement my idea on developing an automation test framework that can fix locator related issues by itself. My abstract idea is as given below. I will have a Selenium Test ...
4
votes
1answer
340 views

How do I solve this optimal control problem with reinforcement learning?

I am new to reinforcement learning. I would like to solve an optimal control problem with reinforcement learning. The objective is for a wolf to catch a rabbit. The wolf and the rabbit run on a ...
2
votes
0answers
143 views

Coloring graphs with reinforcement learning

I am trying to build an RL agent to solve the NP-hard problem graph coloring. The problem is quite challenging. This how I addressed it. The environment To preserve the scalability of the ...
4
votes
1answer
85 views

How would an AI work out this question?

I am trying to create an AI that makes reasonable guesses at truths of statements. However... Human: "Prove that no number exists which is one more than a billion." AI: "Is it true for the number 1? ...
2
votes
0answers
108 views

What is ratio of the objective function in the case of continuous action spaces?

I'm trying to implement the proximal policy optimization (PPO) algorithm. I'm confused on how to make it work with continuous action space. For discrete action space, the output of the network is the ...
3
votes
0answers
90 views

How can I use Q-learning for inventory decision making?

I am trying to model operational decisions in inventory control. The control policy is base stock with a fixed stock level of $S$. That is replenishment orders are placed for every demand arrival to ...
4
votes
2answers
91 views

Can a data compression function be used to make predictions?

I've heard that prediction is equivalent to data compression. Is there a way to take a compression function and use it to create an AI that predicts?
3
votes
1answer
128 views

Is it possible to have a dynamic $Q$-function?

I am trying to use Q-learning for energy optimization. I only wish to have states that will be visited by the learning agent, and, for each state, I have a function that generates possible actions, so ...
6
votes
1answer
82 views

Suicide Predictor and Locator

Suicide is on the increase in my country and most victims tend to leave early traces from text messages, social media accounts, search engine queries. So I came up with the idea to develop an AI ...
2
votes
1answer
68 views

How should I detect an object in a camera image?

I would like to create a model, that will tell me if one type of object is in an image or not. So, for example, I have a camera and I would like to see when one object gets into the shot. Object ...
1
vote
0answers
51 views

Can an AI simulate someone that is diagnosed as “Special Needs”?

Do you think it would be possible to train an AI in such a way as to mimic/simulate someone that is diagnosed as "Special Needs"? Why? Most diagnosis and treatments for people today are subjective, ...
2
votes
0answers
49 views

How should I build an AI that quickly detects falling game assets on screen?

I want to build an AI that plays a simple android game. The game is just a one at a time object falling, some times at an angle. The AI needs to recognize the object and to decide whether to swipe ...
2
votes
0answers
55 views

Which loss functions for transforming a density function to another density function?

I am looking at a problem which can be distilled as follows: I have a phenomenon which can be modeled as a probability density function which is "messy" in that it sums to unity over its support but ...
1
vote
1answer
322 views

How can I encode states where the environment consists of multiple identical elements, but each is characterised by different features?

I am quite new to Deep Reinforcement Learning, and I'm trying to define states in a Reinforcement Learning problem. The environment consists of multiple identical elements, and each one of them is ...
3
votes
2answers
101 views

Which online machine learning technique to use for multi-class classification problem with multiple inputs?

I have the following problem. We have $4$ separate discrete inputs, which can take any integer value between $-63$ and $63$. The output is also supposed to be a discrete value between $-63$ and $63$. ...
4
votes
1answer
50 views

Why not go another layer deeper with Auto-AutoML?

So I'm finding AutoML to be pretty interesting but I'm still learning how it all works. I've played with the incredibly broken AutoKeras and got some decent results. The question is, if you are using ...
1
vote
1answer
100 views

How to deal with invalid output in a policy network? [duplicate]

I am interested in creating a neural network-based engine for chess. It uses a $8 \times 8 \times 73$ output space for each possible move as proposed in the Alpha Zero paper: Mastering Chess and Shogi ...
1
vote
0answers
65 views

How should I deal with vector states in reinforcement learning? [closed]

I am wondering if anyone has any experience dealing with vector states, that is, a state that has multiple values. I cannot find any coding examples online and I am trying to implement Q-learning. Any ...
2
votes
0answers
108 views

Application of Blockchain in Fraud detection in stock market

I want to develop a fraud detection application in the stock market Using Blockchain technology, we have some pattern that defines the anomaly for use of supervised machine learning but there is one ...
4
votes
1answer
155 views

How should I design the LSTM architecture for multivariate time series forecasting problems?

There is plenty of literature describing LSTMs in a lot of detail and how to use them for multi-variate or uni-variate forecasting problems. What I couldn't find though, is any papers or discussions ...
15
votes
1answer
3k views

When should I use Reinforcement Learning vs PID Control?

When designing solutions to problems such as the Lunar Lander on OpenAIGym, Reinforcement Learning is a tempting means of giving the agent adequate action control so as to successfully land. But ...
2
votes
1answer
65 views

What are the known ways to test AI black boxes? [closed]

Is there any conmprehensive paper or site that describes an overview of the known black box testing techniques?
5
votes
1answer
137 views

Are the ideas in the paper “Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour” novel?

In the paper Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour, the authors seem to be presenting a black box method of testing. Are these ideas really new? Weren't these ...
3
votes
1answer
122 views

How do I solve the problem of positioning 11 pieces into a 8x8 puzzle?

I was trying to figure out how to create a solver to the puzzle of putting 11 pieces in a board (8 x 8). I created the game in http://www.xams.com.br/quebra. It is possible to turn the piece 90 ...
1
vote
0answers
320 views

Do we need to use the experience replay buffer with the A3C algorithm?

I have skimmed through a bunch of deep learning books, but I have not yet understood whether we must use the experience replay buffer with the A3C algorithm. The approached I used is the following: ...
2
votes
1answer
30 views

Adding input features - is complete re-training required?

I've never worked with very large models that require weeks or months of training, but in such a situation, what happens if you want to add extra features inputs, do you need to re-train the entire ...
2
votes
1answer
31 views

Changing the batch, mini-batch and learning rate for a previously-trained model

If I'd previously trained a model and saved the whole training session (using TensorFlow tf.train.Saver.save()), and then later restored the session (using ...
0
votes
1answer
40 views

Edge AI device to run inference

I'm trying to figure out what's the best way to get a trained model that does facial detection to run on a camera that's connected to a computer and perform inference. Since I don't need the device ...
4
votes
3answers
192 views

Will we be able to build an artificial intelligence that feels empathy?

Nowadays, robots or artificial agents often only perform the specific task they have been programmed to do. Will we be able to build an artificial intelligence that feels empathy, that understands ...
4
votes
1answer
48 views

How should I encode a categorical input?

Let's say you have an input which can take one of 10 different unique values. How would you encode it? Have input length 10 and one-hot encode it. Have 1 input but normalise the value between the ...
2
votes
1answer
614 views

How do I choose the number of neurons in the fully-connected layer before the softmax layer?

I am solving a classification problem with CNN. The number of classes is 5. How can I decide the number of neurons in the FC layer before the softmax layer? Is it $N * 5$, where $N$ is the number of ...