Skip to main content

Questions tagged [ai-design]

For questions related to the design of AI agents, algorithms, or models. If your question is about designing neural networks, reward functions, or fitness functions, you can use the associated more specific tags "neural-network-design", "reward-design" and "fitness-design", respectively.

101 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
8 votes
2 answers
447 views

How can I solve the zero subset sum problem with hill climbing?

I want to solve the zero subset sum problem with the hill-climbing algorithm, but I am not sure I found a good state space for this. Here is the problem: consider we have a set of numbers and we want ...
K.N's user avatar
  • 181
4 votes
0 answers
372 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 ...
Bridgeburners's user avatar
3 votes
0 answers
146 views

What are the guidelines for defining a reward function in reinforcement learning (bandit problem)?

I'm working currently on a problem and I'm using RL (bandit problem). In my system, I have an agent that chooses an action among $k$ possible actions, and a user that decides whether the agent ...
Walid's user avatar
  • 31
3 votes
0 answers
67 views

What can model everything?

I've been thinking about what "mathematical model" can be used to model every possible thing (including itself). Examples: a simple neuron network models a function but doesn't model an algorithm. A ...
RationalFragile's user avatar
3 votes
0 answers
280 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 ...
Ahmed Rebei's user avatar
3 votes
0 answers
94 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 ...
ranya's user avatar
  • 31
3 votes
2 answers
254 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 $63$. ...
John Mayer's user avatar
3 votes
0 answers
259 views

What can be considered a deep recurrent neural network?

In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the DRQN is described as DQN with the first post-convolutional fully-connected layer replaced by a recurrent LSTM. I have DQN ...
Savco's user avatar
  • 61
3 votes
2 answers
217 views

How to design a recommendation system for shift swapping?

I need to design an algorithm such that it handles the request for shift swapping. The algorithm will recommend a list of people who are more likely to swap that shift with the person by analyzing ...
Paras's user avatar
  • 131
3 votes
0 answers
116 views

NLP proved against US legal texts

I'm new to AI development and am looking for a quality algorithm (potentially nlp?) implementation proved against US legal texts. Obviously some training would need to be done, but I've found little ...
Chris Giddings's user avatar
3 votes
0 answers
215 views

Has anyone used YodaQA for natural language processing?

Has anyone used YodaQA for natural language processing? How easy is it to link to a document database other than Wikipedia? We're thinking we can create a bot to use AI to analyze our developer and ...
Charles Miller's user avatar
2 votes
0 answers
62 views

Is there a state-based approach to neural networks?

It occurred to me that neural networks operate like straight-line programs: an input is processed once by the layers, and an output is always immediately formed, in the same amount of time for each ...
HiddenBabel's user avatar
2 votes
0 answers
171 views

What to look out for when designing an environment regarding observations?

When designing an environment, what should one look out for when designing the observation space to make the environment as easy to be learnable for an agent as possible? E.g. make sure the markov ...
kitaird's user avatar
  • 115
2 votes
0 answers
187 views

How to translate sudoku XV boards in CNF format?

I'm trying to implement the logic for a Sudoku XV puzzle, that it's essentially a standard sudoku with the addition of X and V markers between some pairs of squares. X markers in adjacent pairs ...
WebStormer's user avatar
2 votes
0 answers
56 views

How can I formulate a prediction problem (given labeled data) as an RL problem and solve it with Q-learning?

One of my friends sent me a problem he was working on lately, and I couldn't help but I wonder how could it be solved using Q-learning. The statement is as follows: Given the following datasets, the ...
Conny's user avatar
  • 21
2 votes
1 answer
325 views

How to implement RAM versions of Atari games

I have coded the breakout RAM version, but, unfortunately, its highest reward was 5. I trained it for about 2 hours and never reached a higher score. The code is huge, so I can't paste here, but, in ...
dato nefaridze's user avatar
2 votes
0 answers
48 views

Is there an online RL algorithm that receives as input a camera frame and produces an action as output?

I want to build a reinforcement learning model, which takes a camera picture as input, that learns online (in terms of machine learning). Based on the position of an object on the camera, I want the ...
Wuuhi's user avatar
  • 21
2 votes
0 answers
920 views

Wooden railway search problem AI

I have this problem. A basic wooden railway set contains the pieces shown in Figure 3.32. The task is to connect these pieces into a railway that has no overlapping tracks and no loose ends where a ...
rucarr's user avatar
  • 21
2 votes
0 answers
340 views

Which activation functions should I use for polynomial regression?

I am a beginner in machine learning and neural networks. I have only used neural networks for classification problems. My aim is to modify it so that it can work for polynomial regression as well. In ...
isaac john's user avatar
2 votes
0 answers
58 views

How can I formalise a non-zero-sum game of $N$ agent as Markov game?

I coded a non-zero-sum game of $N$ agents in a discrete dynamic environment to RL with Q-learning and DQN agents. It's like a marathon. Only two actions are available per agent: $\{ G \text{ (move ...
mehmet's user avatar
  • 21
2 votes
0 answers
50 views

How should I define the reward function for the Connect Four game?

I'm creating an RL application for the game Connect Four. I've researched the different strategies for the game and which positions are more favourable to lead to a win. Should I be assigning ...
mason7663's user avatar
  • 613
2 votes
0 answers
33 views

Language Learning feedback with AI

Is there a program under development that uses AI technology, like Siri, to "hold hands" so to speak with a language learner and coach them on accent, colloqiual expressions, or to let them guide the ...
Tristan Beckwith's user avatar
2 votes
0 answers
83 views

Best AI Approach for 2D to-down space shooter

I am building a 2d top-down space game, which involves several objects, such as asteroids, drones, spaceships, space litter and power-ups. It follows the rules of space gravity, with speed and ...
user9927059's user avatar
2 votes
0 answers
101 views

How can I predict the nutrients in dishes given the ingredients used to prepare them?

I want to know which algorithm will work most efficiently for calculating nutrients present in a food dish if I am giving the ingredients used in the food. Basically, let us assume that I want to make ...
Neel Modi's user avatar
2 votes
0 answers
120 views

How can I assign agents to tasks based on time and affinity?

I am working on an assignment problem. Consider $K$ agents $A_1, \dots A_K$ and $N$ tasks $T_1, \dots T_N$. Each task has a certain time $t(T_i)$ to be completed and each agent has a matching (or ...
Tariq Kavish Arain's user avatar
2 votes
0 answers
54 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 ...
alt-rose's user avatar
  • 121
2 votes
0 answers
145 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 ...
Omri Gelman's user avatar
2 votes
0 answers
59 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 ...
roydouek's user avatar
2 votes
0 answers
104 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 ...
Novak's user avatar
  • 161
2 votes
0 answers
139 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 ...
R1-'s user avatar
  • 137
2 votes
0 answers
59 views

What methods are there to detect discrimination in trained models?

I've been researching AI regulation and compliance (see my related question on law.stackexchange), and one of the big take-aways that I had is that the regulations that apply to a human will apply to ...
Bruce Pulley's user avatar
2 votes
0 answers
149 views

Can this problem be solved by AI?

I am looking in to building a kind of troubleshooting web application. It would be a form that starts with a first question. Depending on the answer, you get a follow up question and so on until the ...
Martin Larsson's user avatar
2 votes
0 answers
86 views

How would I implement this New Type of NN

CIO NN CIO NN stands for Controller Input Output Nerual Network note due to a typo the "nearon" means "neron" For this we have to redefine the Nearon 2 Inputs 2 Outputs 4 Weights (each input and ...
X3R0's user avatar
  • 211
1 vote
1 answer
175 views

Where would If my goal was to do OCR pdf text extraction on 1000s of PDFs I have?

So I have lots of data (pdfs) that I want to train an AI model to extract info from. All of them are a little different but have the same key data points. Is it possible to train an AI on the pdfs I ...
Alen Ramic's user avatar
1 vote
0 answers
108 views

How to represent multiple-output logic circuits in tree-based genetic programming

Consider the following digital logic circuit, which has multiple inputs and one output: The logic circuit above can be represented in tree form: This tree representation could then be used in a tree-...
Flux's user avatar
  • 123
1 vote
0 answers
32 views

Derive information for sub-scoring from one scoring model

I am currently working in Python with a random forest algorithm to perform a scoring. My output is binary. The idea now is to derive sub-scores from the above model that give an opinion on different ...
lari1995's user avatar
1 vote
0 answers
107 views

Might AGI need to be flawed?

An example is the halting problem, which states computing cannot be solved by exhaustion, but which humans avoid trivially by becoming exhausted. Humans typically give up what seems like a lost cause ...
DukeZhou's user avatar
  • 6,237
1 vote
0 answers
50 views

AI approach for layout mapping

I am researching different AI approaches and was curious what approach would be useful in my scenario. Assume you are tiling a room. The tiles, and the room itself, can be any shape. In this room you ...
user3010406's user avatar
1 vote
0 answers
158 views

How to design my Neural Network for Game AI

For my school project, I have to develop an agent to play my game. The base I have is a 'GameManager' which call 2 AIs, each taking a random move to do. To make my AI perform, I decided to make a ...
Benjamin Darras's user avatar
1 vote
0 answers
50 views

How to find a parameter combination for a black box using AI?

I am working on a project where I encountered a component which takes 96 arguments (all integer values) and outputs 12 float values. I would like to find a useful combination of these 96 values to ...
e.Fro's user avatar
  • 186
1 vote
2 answers
127 views

How to train a model to predict the number of people at a certain bus stop before they cumulate in large numbers?

Each person probably uses an app that tracks his/her position periodically and sends it to our servers. What I want is to use these data to train a model to predict the rush hours of each bus-stop on ...
Alaa Sabateen's user avatar
1 vote
0 answers
45 views

How can one be sure that a particular neural network architecture would work?

Traditionally, when working with tabular data, one can be sure(or at least know) that a model works because the included features could explain a target variable, say "Price of a ticket" ...
Naveen Reddy Marthala's user avatar
1 vote
0 answers
49 views

Can text-independent writer identification be done without multi-sentence training datasets for each writer?

I am trying to learn more about text-independent writer identification and was hoping for some advice. I have a folder with 100k images, each of them with a different handwritten sentence. All of the ...
user38553's user avatar
1 vote
0 answers
40 views

How to design a graph neural network to predict the forces in truss elements of a space frame?

I am trying to create a Graph NN that will be able to predict the forces in truss elements of a space frame. The input for the NN will be a graph, where the nodes represent the nodes of the spaceframe....
oatless's user avatar
  • 11
1 vote
0 answers
21 views

How to autocorelate multiple variants of same text into one?

I want to improve quality of translations for open-source projects in Ukrainian language. We have multiple translations from different authors. We can also translate messages using machine ...
Volodymyr M. Lisivka's user avatar
1 vote
0 answers
1k views

How to compare SegNet, U-Net and EfficientNet?

SegNet and U-Net are created for segmentation problem and EfficientNet is created for classification problem. I have a task and it is saying that train these models on the same dataset and compare ...
Ugurcan's user avatar
  • 121
1 vote
0 answers
178 views

Can SqueezeNet be used for regression?

I want a model that outputs the pixel coordinates of the tip of my forefinger, and whether it's touching something or not. Those would be 3 output neurons: 2 for the X-Y coordinates and 1, with a ...
Orly's user avatar
  • 71
1 vote
0 answers
116 views

Automating browser actions using AI

I am at a very initial stage of my research so I will try to describe what I am trying to achieve: I want to create an AI model which learns how to navigate the browser's component like clicking or ...
Aditya Kushwah's user avatar
1 vote
0 answers
26 views

How can I design a system that suggests physical exercises to a person while keeping into account the fatigue?

I want to create an exercise suggester. Each day either has a routine or is a rest day. A routine has 4 slots. For each slot we select an exercise. We constrain the legal exercises, only do upper-body ...
Just_Alex's user avatar
  • 151
1 vote
0 answers
43 views

How can I approximate a function that determines the priority of objects?

I am facing the following supervised learning problem: An object is fully characterized by its position in $R^n$. There are $m$ objects. There are fully observable (i.e. their positions are always ...
Vince's user avatar
  • 111