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 [ai-design]

For questions related to successful or novel designing standards and procedures of Artificially Intelligent agents.

0
votes
0answers
3 views

My iterative deepening engine doesn't have an exactly equal score when playing against itself

I made a Connect Four engine that uses the standard minimax/alpha-beta algorithms as its underlying structure, with iterative deepening added on. Because the engine uses iterative deepening, its ...
4
votes
1answer
30 views

Building AI from chess - data shape from simulation

Problem My problem is the following: Given 1000 wins, losses, and ties from a chess simulation I am using, what shape should each game be (I.e., sequence of moves leading to win/loss/tie) in order to ...
0
votes
1answer
19 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 ...
2
votes
1answer
55 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,...
2
votes
1answer
30 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 ...
1
vote
0answers
11 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 ...
2
votes
0answers
13 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
53 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 ...
4
votes
3answers
142 views

Can artificial intelligence be hacked or not?

Can artificial intelligence be hacked or not by using enough computing skills or by other cryptography methods? So are we able to say that AI is one of in its secured form?
0
votes
1answer
43 views

Tensorflow - finding the right model on my use case

The Levenshtein algorithm and some ratio and proportion may handle this use case. Based on the pre-defined sequence of statements, such as "I have a dog", "I own a car" and many more, I must ...
0
votes
0answers
20 views

Smart, energy efficient refrigerator design?

Opportunities For Creative Minds Do any members of this AI StackExchange have any new and creative design ideas about how to use existing AI technology to make any of the below refrigerator features ...
6
votes
1answer
53 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 ...
0
votes
0answers
25 views

Testing of game engines

I have implemented a checker's game engine in C. I would like to know how to go about setting up a benchmark for my engine so I can decide if it is performing intelligently.
0
votes
0answers
13 views

CheckerBoard interface

I have downloaded the CheckerBoard program (shown below) but I cannot understand what is meant by primary and secondary engines. Does it mean the white is the primary engine and the red uses the ...
2
votes
0answers
28 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
19 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 ...
5
votes
2answers
65 views

What are ontologies in AI?

Can anyone explain to me what exactly ontologies are in AI? How should I write them and why are they important? I can't seem to find relevant information on Google.
1
vote
0answers
19 views

Semantics of natural language — is AI capable hardware and software now developed enough to realize it?

The need for semantic cognition in relation to natural language in computers is ever appearing in real problems in the field of AI. We can note a substantial increase in related posted in ...
0
votes
0answers
12 views

How to model Tangram in search space.

I wonder if there is a such model of the Tangram game so that it can be solved by search tree techniques,but the main problem is how to represent the all the states, if any, since given a ...
0
votes
1answer
35 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
14 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 ...
4
votes
1answer
68 views

AlphaZero policy network

In AlphaZero, the policy (head of the) network maps game states to a distribution of the likelihood of taking each more. This distribution covers all possible moves from that state. How is such a ...
3
votes
1answer
61 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
92 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
68 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
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. ...
4
votes
1answer
226 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 ...
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 ...
12
votes
2answers
427 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 ...
2
votes
0answers
82 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-...
4
votes
2answers
52 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
27 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
90 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
26 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 ...
2
votes
1answer
51 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, ...
3
votes
5answers
184 views

AI Beginners Book

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. ...
7
votes
1answer
134 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
114 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
54 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 "...
23
votes
9answers
4k views

Is Artificial Intelligence Vulnerable To Hacking?

"The Limitations of Deep Learning in Adversarial Settings" (PDF) explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. ...
3
votes
1answer
60 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
122 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
1answer
20 views

Why are GRU and LSTM better than old types of RNN?

Seems older RNNs have a limitation for their use cases and have been outperformed by other architectures for specific tasks e.g GRUS and CNNs
0
votes
1answer
144 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
162 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 ...
-1
votes
1answer
60 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
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 ...
2
votes
3answers
113 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
72 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
45 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 ...