Questions tagged [ai-design]

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

Filter by
Sorted by
Tagged with
2
votes
3answers
233 views

How would AI prioritize situational ethics?

There's a real possibility that self driving cars become more than just a high tech novelty and they start changing the market. As seen in Logan, self driven commercial freight might be among the ...
3
votes
0answers
79 views

How to define an action space when an agent can take multiple sub-actions in a step?

I'm attempting to design an action space in OpenAI's gym and hitting the following roadblock. I've looked at this post which is closely related but subtly different. The environment I'm writing needs ...
7
votes
2answers
2k views

What are the most important components in the algorithm of a minimum AI?

If someone wants to develop a basic AI with some code modules,Let us say the AI just has to provide an action when stimulated in a certain situation based on its previous understanding of situations. ...
14
votes
2answers
418 views

How should I encode the structure of a neural network into a genome?

For a deterministic problem space, I need to find a neural network with the optimal node and link structure. I want to use a genetic algorithm to simulate many neural networks to find the best network ...
9
votes
1answer
394 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 ...
5
votes
3answers
251 views

Given enough computational resources, do we currently have any algorithms which could achieve AI?

Hypothetically, assume that you have access to infinite computing power. Do we have designs for any brute-force algorithms that can find an AI capable of passing traditional tests (e.g. Turing, ...
6
votes
4answers
1k views

Can prior knowledge be encoded in deep neural networks?

I was reading Gary Marcus's a Critical Appraisal of Deep Learning. And one of his criticisms is that neural networks don't incorporate prior knowledge in tackling a problem. My question is, has there ...
4
votes
2answers
332 views

What kind of Algorithm is used is StackGAN to process realistic Images

How does StackGAN processes such a realistic image just from collecting details in the text? What kind of algorithm is used behind it? Anyone have any idea? Please Share.
4
votes
2answers
159 views

Is “emotion” ever used in AI?

Is "emotion" ever used in AI? Psychologists have a lot to say about emotion and it's functional utility for survival - but I've never seen any AI research that uses something resembling "emotion" ...
4
votes
1answer
437 views

How would you encode your input vector/matrix from a sequence of moves in game like tasks to train an AI? e.g. Chess AI?

I've seen data sets for classification / regressions tasks in domains such as credit default detection, object identification in an image, stock price prediction etc. All of these data sets could ...
2
votes
1answer
303 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 ...
2
votes
1answer
135 views

How to train a reinforcement learning agent from raw pixels?

How would you train a reinforcement learning agent from raw pixels? For example, if you have 3 stacked images to sense motion, then how would you pass them to neural networks to output Q-learning ...
4
votes
2answers
154 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. ...
4
votes
2answers
104 views

Why do we need both the validation set and test set?

I know that this has been asked a hundred times before, however, I was not able to find a question (and an answer) which actually answered what I wanted to know, respectively, which explained it in a ...
3
votes
1answer
110 views

How would one go about generating *sensible* responses to chat?

I have recently gone about and made a simple AI, one that gives responses to an input (albeit completely irrelevant and nonsensical ones), using Synaptic.js. Unfortunately, this is not the type of ...
3
votes
1answer
505 views

What are the (general) sizes of AlphaGo and Deep Blue?

I'm trying to get a gauge on just how big the programs and databases are these automata. I understand that this is a changing number, particularly in regard to Machine Learning. Q: How large was ...
3
votes
0answers
152 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 ...