Questions tagged [theory]

Use for questions on AI theory and other theoretical subjects related to AI.

Filter by
Sorted by
Tagged with
3
votes
0answers
30 views

Is it possible to control asymptotic behaviour of neural network models?

Is it possible to specify what the asymptotic behaviour of a Neural Networks (NN) model should be? I am thinking on NN which try to learn a mapping $\vec y=f(\vec x)$ with $\vec x$ a vector of ...
5
votes
9answers
515 views

Can Neural Networks self-optimize?

Suppose that you show a neural network its own code, and allow it to edit itself? Can a neural network modify its own weights and architecture (the number of layers, the number of neurons per layer, ...
37
votes
4answers
9k views

Are neural networks prone to catastrophic forgetting?

Imagine you show a neural network a picture of a lion 100 times and label with "dangerous", so it learns that lions are dangerous. Now imagine that previously you have shown it millions of images of ...
0
votes
0answers
68 views

Help and guide books in the study of AI

Useful knowledge is costly to obtain. Above all books require a substantial investment. I have bought 6 books on AI. For ...
2
votes
0answers
38 views

Why do neural networks have bias units?

Why do neural networks have bias units? Why is it sometimes okay to opt them out?
1
vote
1answer
86 views

What is an agent in Artificial Intelligence?

While studying artificial intelligence, I have often encountered the term "agent" (often autonomous, intelligent). For instance, in fields such as Reinforcement Learning, Multi-Agent Systems, Game ...
2
votes
1answer
32 views

Is explainable AI more feasible through symbolic AI or soft computing?

Is explainable AI more feasible through symbolic AI or soft computing? How much each paradigm, symbolic AI and soft computing (or hydrid approaches), adresses explanation and argumentation, where ...
2
votes
2answers
84 views

Would an artificial general intelligence have to be Turing complete?

Artificial general intelligence is the intelligence of a machine that could successfully perform any intellectual task that a human being can. Would an artificial general intelligence have to be ...
2
votes
1answer
53 views

What are the known ways to test AI black boxes?

Is there any conmprehensive paper or site that describes an overview of the known black box testing techniques?
1
vote
0answers
16 views

Theoretical grounding for ease of training with a prior

If we have a neural network that learns the generative model for P(A, B, C) And now, we want to learn the generative model for P(A, B, C, D) Is there any theory that says learning P(A,B,C) and then ...
0
votes
0answers
19 views

Superhuman AI to disguise as human players

TL;DR below. You entered a online mini video game. It's a fast-paced hypercasual game. But it's a ranked one - top 10 get prizes. The leaderboard resets and prizes are handed out every couple of ...
2
votes
1answer
74 views

Neural nets need a short term memory of some sort

I notice with the recent revelation of severe limitations in some AI domains such as self driving cars that NNets behave with the same sort of errors as in simpler models. Ie: They may be ~100% ...
1
vote
1answer
28 views

Is Intelligence a naturally occurring function of Information Technology?

Here intelligence is defined as any analytic or decision making process, regardless of strength (utility), and, potentially, any process of computation that produces output, regardless of the medium. ...
1
vote
3answers
58 views

Are winning and imitating the primary indicators of intelligence?

Conjecture 1: The smartest chess playing system is the one that wins the tournament. Conjecture 2: The computer system that imitates human dialog is as smart as the human whose dialog was imitated. ...
1
vote
1answer
70 views

How would a quantum computer potentially facilitate artificial consciousness, assuming it is possible?

How would a quantum computer potentially facilitate artificial consciousness, assuming it is possible?
3
votes
0answers
20 views

Batch PTA stopping condition

I am reviewing my Neural Network lectures and I have a doubt: My book's (Haykin) batch PTA describes a cost function which is defined over the set of the misclassified inputs. I have always been ...
1
vote
0answers
65 views

An idea I had to create the first Humanoid using Deep Learning

I've come up with an idea on how we could use a combination of Deep Learning and body sensors to create a walking talking living humanoid. Here goes: First, we will recruit 1 billion people and have ...
7
votes
4answers
96 views

What does learning mean?

Can someone explain what is the process of learning? What does it mean to learn something?
3
votes
1answer
111 views

Are human brain processes, like intuition or imagination, algorithmic?

Are human brain processes, like intuition, creativity, imagination and the ability to create art, algorithmic processes (that is, produced by an algorithm)?
0
votes
1answer
73 views

How can I systematically learn about the theory of neural networks?

I have seen a few articles about neural nets. Mostly they went along these lines: we tried these architectures, these meta parameters, we trained it for $x$ hours on $y$ CPUs, and it gave us these ...
2
votes
2answers
58 views

Will a neural network always predict the correct label if it sees the exact same input during training and testing?

If I'm performing a text classification task using a model built in Keras, and for example, am attempting to predict the appropriate tag given a Stack Overflow question: "how to subtract 1 from an ...
3
votes
3answers
261 views

If AI can perceive, can it be sentient? [duplicate]

I think that AI perceive the world. Can an AI be sentient?
0
votes
1answer
27 views

Is AI truly doing anything that we can consider ''intelligent'' outside of subjective perception of what we perceive to function?

Artificial intelligence seems like a modelling program for interfaces of possible processes forming into another possible or greater architectures of further or differing processes. In what capacity ...
1
vote
1answer
76 views

How important are notations for Artificial Intelligence?

According to WIkipedia, a notation is a semiotics term to describe artistic disciplines. Famous examples are: chess notation, Siteswap notation for juggling, Labanotation for dancing, basketball play ...
1
vote
1answer
73 views

Can I filter barking sounds on the television?

My dog goes bonkers every time the sound of a barking dog is heard on a television program. I never noticed this before but literally every movie or show with an outdoors setting eventually includes ...
3
votes
1answer
226 views

Why does the “reward to go” trick in policy gradient methods work?

In policy gradient method, there's a trick to reduce a variance of policy gradient. We use causality, and remove part of the sum over rewards so that only actions happened after the reward are taken ...
1
vote
0answers
35 views

How Dempster-Shafer theory work in AI?

How does Dempster-Shafer theory work in representing ignorance in AI field?
4
votes
3answers
116 views

Is an algorithm that is no longer actively learning an AI?

This question assumes a definition of AI based on machine learning, and was inspired by this fun Technology Review post: SOURCE: Is this AI? We drew you a flowchart to work it out (Karen Hao, MIT ...
1
vote
3answers
159 views

How does Tara AI work?

Cisco and other companies are using Tara AI—a matching tool that connects IT projects with freelancers who have the exact skills required to complete them. Looking for an explanation of how Tara AI ...
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 ...
5
votes
6answers
2k views

What are the most instructive movies about artificial intelligence?

The field of AI has expanded profoundly in recent years, as has public awareness and interest. This includes the arts, where fiction about AI has been popular since at least Isaac Asimov. Films on ...
7
votes
3answers
537 views

What is a learning agent?

What is a learning agent, and how does it work? What are examples of learning agents (e.g., in the field of robotics)?
6
votes
2answers
76 views

How much can the addition of new features improve the performance?

How much can the addition of new features improve the performance of the model during the optimization process? Let's say I have a total of 10 features. Suppose I start the optimisation process using ...
3
votes
2answers
999 views

What is the difference between learning and non-learning agents?

What is the difference between learning agents and other types of agents? In what ways learning agents can be applied? Do learning agents differ from deep learning
10
votes
4answers
222 views

Spontaneous emergence of replicators in Artificial Life

One of the corner stones of The Selfish Gene (Dawkins) is the spontaneous emergence of replicators, i.e. molecules capable of replicating themselves. Has this been modeled in silico in open-ended ...
3
votes
2answers
59 views

The possibility of emerging of the psychology of an artificial intelligence

The question, in short, is: what the possibility of emerging of the new branch of the psychology - the psychology of an artificial intelligence? Possibly as a new branch of an engineering psychology, ...
10
votes
3answers
342 views

Is the singularity something to be taken seriously?

The term Singularity is often used in mainstream media for describing visionary technology. It was introduced by Ray Kurzweil in a popular book The Singularity Is Near: When Humans Transcend Biology (...
4
votes
1answer
109 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 ...
8
votes
4answers
262 views

How do you program fear into a neural network?

If you've been attacked by a spider once chances are you'll never go near a spider again. In a neural network model, having a bad experience with a spider will slightly decrease the probability you ...
4
votes
3answers
91 views

Can we make a chatbot that UNDERSTANDS not just answer questions based on his database?

Can we really make a chatbot that understands (rather than just replies to) questions based on the database/options of replies that it has? I mean, can it come up with correct/non-stupid replies/...
-1
votes
1answer
50 views

How important will statistical learning be to a conscious AI?

Deep learning is based on getting a large number of samples and essentially making statistical deductions and outputting probabilities. On the other hand we have formal programming languages like ...
4
votes
4answers
210 views

What if there's a game where all the AI people actually lived?

Imagine the fictitious scenario in a role playing game (RPG) where the non-playing characters (NPCs) within the RPG are conscious of their own surrounding and consider the developer to be god. The ...
3
votes
4answers
101 views

Could an AI be built to learn based of interaction with a human?

A neural network is usually programmed to learn from datasets to solve a specific problem. Essentially, they perform non-linear regression. Could a neural network be programmed to receive input from ...
3
votes
2answers
104 views

Google's Principles of Artificial Intelligence

Earlier this month, Google released a set of principles governing their AI development initiatives. The stated principles are: Objectives for AI Applications: Be socially beneficial. ...
1
vote
4answers
239 views

Can an AI distinguish between good and bad according to people living in a restricted geographical area?

Would people go far with Artificial Intelligence and machine learning to the point where machines could learn during a long period of time to distinguish what's 'good' from 'bad' according to people ...
2
votes
1answer
159 views

Reinforcement Learning over an MDP that is actually a POMDP

Look at Breakout: We know that the underlying world behaves like an MDP, because for the evolution of the system it just need to know which is the current state, i.e. position, speed and speed ...
11
votes
2answers
361 views

Is there any scientific/mathematical argument that prevents deep learning from ever producing strong AI?

I read Judea Pearl's The Book of Why, in which he mentions that deep learning is just a glorified curve fitting technology, and will not be able to produce human-like intelligence. From his book ...
3
votes
2answers
972 views

What should I do when the potential value of a state is too high?

I'm working on a Reinforcement Learning task where I use reward shaping as proposed in the paper Policy invariance under reward transformations: Theory and application to reward shaping (1999) by ...
5
votes
2answers
127 views

Is it possible to build an AI that learns humanity, morally?

It is a new era and people are trying to evolve more in science and technology. Artificial Intelligent is one of the ways to achieve this. We seen lots of examples for AI sequences or a simple "...
7
votes
2answers
103 views

Measuring Soft Skill

How can we attach numerical value to the measurement of soft skill? Is there any book, site or materials that can teach me how to do this? I want to know if there is any way we can measure soft skill ...