We’re rewarding the question askers & reputations are being recalculated! Read more.

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
32 views

Can an artificial network create a rule from rule components?

If an antecedent in a rule involves $m$ two-state features and results in consequences from a set of $n$ possible ones, we have $2^{m+n}$ permutations, which are, in a sense, be categories. If ...
4
votes
4answers
206 views

What kind of algorithm can invent?

Set aside networks, image classification, gradients, and the strength of intelligence for a moment and consider the world before people lit fires. Fires were started periodically just as they are now,...
1
vote
1answer
60 views

Is the proposal that more power leads to more intelligence correct?

One of the somewhat subliminal and entirely unsubstantiated assumptions we hear is that more computing power will allow us to approximate human intelligence — that quantitative augmentation will ...
2
votes
1answer
55 views

Why is Information Filter called Information Filter?

We all know Information Filter is a dual representation of Kalman Filter. The main difference between Information Filter and Kalman Filter is the way the Gaussian belief is represented. In Kalman ...
1
vote
0answers
29 views

Recognition and Response Generalizations for Autonomous Vehicles or Not?

It is said that the number of possible sequences of game play in the game Go is greater than the number of atoms in the universe. Whether or not that is true, imagine the number of possible sequences ...
2
votes
1answer
1k views

How to combine input from different types of data sources?

I've to train a neural network using microphone data (wav files), accelerometer sensor data and light sensor data. Right now the approach I thought was to convert all data into images and combine ...
6
votes
1answer
95 views

Q-Learning the generic maze solution

After doing some exercices on Q-learning for maze solving, I wondered : my q-learning algorithms solve only ONE maze. The AI doesn't learn how to solve mazes, so how can I achieve it ? For instance ...
1
vote
0answers
150 views

How can a fully automated vacuum cleaner use and update room information?

Assistive Subsystems Consider an automated vacuum cleaner with the following subsystems under the command of an AI system to be designed. These subsystems limit the AI complexity to just intelligent ...
2
votes
0answers
41 views

How to use Machine Learning to create a “Draw-A-Person Test”

The process revolves around a child's drawing. Each part of each drawing corresponds to a score as in the Draw a Person Test conceived by Dr. Florence Goodenough in 1926. The goal of the machine is to ...
11
votes
2answers
2k views

What are ontologies in AI?

What exactly are ontologies in AI? How should I write them and why are they important?
0
votes
1answer
41 views

What's the difference between poker with public cards and without them?

Example: texas holdem poker vs texas holdem poker with the same rounds, just with no public cards dealt. Would algorithms like CFR approximate Nash-equilibrium more easily? Could AI that does not ...
1
vote
0answers
18 views

How to handle Feature changes in a model deployed ?

I implemented and deployed with Flask an XGBoost model for a classification problem. But being aware that features importance can change over time to predict probability of label for new data, I ...
5
votes
1answer
808 views

Why does the policy network in AlphaZero work?

In AlphaZero, the policy network (or head of the network) maps game states to a distribution of the likelihood of taking each action. This distribution covers all possible actions from that state. ...
4
votes
1answer
152 views

What does “hard for AI” look like?

In theoretical computer science, there is a massive categorization of the difficulty of various computational problems in terms of their asymptotic worst-time computational complexity. There doesn't ...
6
votes
3answers
280 views

AI composing music

Do you know what AI model would be best for let it learn composing music? I really don't know where to start there. Are there some good papers out there? I would say, if I use a NN, my only option ...
4
votes
1answer
74 views

Approaches to poker tournament winner prediction?

I’ve done my research and could not find answer anywhere else. My apologies in advance if same problem is answered in different terms on stack-overflow. I am trying to solve poker tournament winner ...
3
votes
2answers
82 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. ...
8
votes
1answer
1k views

Is Nassim Taleb right about AI not being able to accurately predict certain types of distributions?

So Taleb has two heuristics to generally describe data distributions. One is Mediocristan, which basically means things that are on a Gaussian distribution such as height and/or weight of people. The ...
10
votes
7answers
3k 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 ...
12
votes
2answers
629 views

Do self-driving cars resort to randomness to make decisions?

I recently heard someone make a statement that when you're designing a self-driving car, you're not building a car but really a computerized driver, so you're trying to model a human mind -- at least ...
1
vote
0answers
112 views

Testing of artificial network hardware acceleration — Any additions?

The Current Plan to Possibly be Augmented TranSeed Labs is testing two PCI express artificial network acceleration products and their SDKs against easy to assemble data sets and demos. Aaeon Up PER-...
1
vote
0answers
77 views

How can I create a chatbot application where the user can create its own bot?

I am trying to create a chatbot application where the user can create its own bot, like Botengine. After going through google, I saw I need some NLP API to process the user's query. As per wit.ai ...
4
votes
2answers
117 views

Loss function for singular object detection

What loss function should one use, knowing that input image contains exactly one target object? I am currently using MSE to predict center of ROI coordinates and it's width and height. All values ...
1
vote
0answers
42 views

Is anyone working on officiated team intelligence or anything like it?

The artificial intelligence topology that does not appear in the machine learning literature to my knowledge is that of officiated teams or round robins of them. The paradigm is a proven one in the ...
3
votes
1answer
152 views

Mathematical modelling of A.I algorithms

How does one even begin to mathematically model an A.I algorithm like alpha-beta pruning or even its thousands of variations, to determine which variation is best?
1
vote
0answers
35 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 ...
3
votes
1answer
80 views

What beginner-friendly machine learning method should I use to make teams for my pickup ultimate frisbee club fairly balanced?

A bunch of friends and I play ultimate every week. Recently I wrote a program to choose our teams for us, as well as keep track of certain data (like which players were on which team, which team won, ...
6
votes
6answers
396 views

AI beginners books for coding

Does anyone know a good book to buy for beginners to coding for artificial intelligence? I have done some coding in Java and a little with Python, but I would be willing to learn a new language too.
9
votes
1answer
277 views

What tools are used to deal with adversarial examples problem?

The problem of adversarial examples is known to be critical for neural networks. For example, an image classifier can be manipulated by additively superimposing a different low amplitude image to each ...
4
votes
3answers
150 views

Are Neural Net architectures accidental discoveries?

So recently I have been learning about new NN's which are used for specialised purposes like speech recognition, image recognition, etc. The more I discover the more I get amazed by the cleverness ...
1
vote
0answers
58 views

How basically AI synthesize thinking?

In the instance like AlphaGo Zero. How N' why AlphaGo Zero's training is so stable? Compared with traditional game theory applied in Deep RN technique!? How "AlphaGo Zero" differs from "...
3
votes
1answer
137 views

Minimax with only max

If both the players want to increase their score (by selecting the highest/best cost path) can this be done using Minimax Algorithm and not other algorithms?
2
votes
1answer
162 views

Elon musk's comment on “non-benign AI scenarios”

I watched a youtube clip of Elon Musk talking about his view on the future of AI. He gave two examples. One of the examples was a benign scenario and the other example was a non benign scenario where ...
2
votes
5answers
304 views

How can we define common sense in an AI agent?

In our lives, we meet different people and describe their common sense based on how they act on a situation. For example, highly extrovert people are able to deal with people without any awkwardness. ...
0
votes
1answer
154 views

I want to learn about AI any suggestions? [closed]

I'm currently a software developer, and I want to get into this field, I'm interested particularly in self driving cars, which as far as I know, work with AI or machine learning (which I still don't ...
5
votes
2answers
214 views

What functionality, does control look like in autonomous vehicles levels 4 and 5?

We are doing a research design project on autonomous vehicles and have some questions on AV Levels 4/5; specifically on the roles, impacts and consequences of AV on society, government, users and ...
-2
votes
1answer
66 views

Help me with my final project for my last year college [closed]

my name is iSlam, industrial designer from Egypt, it’s my last year and the project i want to make something like smart home system with voice control, can anyone help me with any advice.
4
votes
1answer
73 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 ...
3
votes
3answers
126 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 ...
2
votes
2answers
84 views

AI Knowledge Based System: I am having difficulties understanding proposition logic

I am having difficulties wrapping my head around how the answer is being produced. How does the solution come up with the answer 3? How does one derive the answer 3 from the truth table? For example ...
3
votes
1answer
74 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 ...
4
votes
4answers
2k views

Learning Artificial Intelligence with Python vs. Java

I am a University student taking an Artificial Intelligence class this semester. Our Professor's programming language of choice is Java, but it seems that perhaps with some nudging, he can change it ...
1
vote
1answer
106 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- ...
2
votes
2answers
402 views

Input optimization on a supervised learning system

Problem Given a collection of pairs (X, y) where X belongs to R^n and y belongs to R, find the X such that the associated y would be maximum. Example Given: (X=(1, 2), y=-9) (X=(-2, 4), y=-36) (X=...
1
vote
1answer
86 views

Which edges of this tree will be pruned by Alpha-beta pruning?

So I know that 'h' and 'f' will be pruned, but I'm not sure about 'k' and 'l'. When we visit 'j', technically there is no need for us to visit 'k' and 'l' because there are 2 options: one or two of ...
4
votes
2answers
88 views

What model to use for fully unbalanced data?

I am working on an anti-fraud project. In the project, we are trying to predict the fraud user in the out time data set. But the fraud user has a very low ratio, only 3%. We expect a model with a ...
2
votes
1answer
262 views

AI chatbot design

I am looking to train a chatbot that can help me relieve stress and deal with my negative emotions. I would like for the chatbot to be like the ones that pass the Turing test, remain professional, yet ...
1
vote
0answers
26 views

Whats advantages does a Loop Network have over a Feed Forward Network?

I am interested to see what advantages a Loop Network (Feed Forward Network that takes its output as input, I think it's called an RNN, not sure). The only result I found was that it was extremely ...
1
vote
0answers
78 views

Design neural network for generating sorting networks

How would you design a neural network that generates the positions of comparators in a sorting network given a set of numbers. I've tried to modify some already implemented networks that given a set ...
4
votes
1answer
68 views

Whats the correct technique/technology to identify duplicate data

We store supplier information for many companies. Each supplier database is logically separated, making it possible for a supplier to be common across logical separations. At the moment, we have ...