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 [theorics]

Use for questions related to theoretical subjects and questions.

0
votes
0answers
30 views

Is my cart-pole agent behavior expected under these circumstances?

I'm trying to solve the cart-pole problem from Open-AI. For this task I'm using a one step actor-critic algorithm. The purpose of this implementation is mainly to study. For this reason I'm using a ...
8
votes
2answers
152 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 in 2005. (1) In his book, Kurzweil gives an outlook to ...
3
votes
1answer
55 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 ...
5
votes
2answers
365 views

Why does the discount rate (γ) in the Monte-Carlo Policy-Gradient Method (episodic) appears twice?

I was reading the book Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto (complete draft, November 5, 2017). On page 271, the pseudo-code for the episodic Monte-Carlo ...
7
votes
3answers
153 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
65 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
43 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
169 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
3answers
51 views

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

Following my recent chat on this network, I have been advised to form this question. Background: Currently a neural network or deep-learning/machine learning is programmed to interact with specific ...
3
votes
2answers
59 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
2answers
91 views

Limits of artificial emotional intelligence?

I would like to know: 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'...
2
votes
1answer
74 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 ...
7
votes
1answer
163 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 ...
1
vote
2answers
116 views

Potential-based Reward Shaping gives too negative reward

I'm working on a Reinforcement Learning task where I use reward shaping as proposed in [1]. In short, my reward function has this form: ...
4
votes
1answer
78 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 "...
3
votes
7answers
219 views

Why are we asking, “How can we simulate the brain?”

As I've thought about AI, and what I understand of the problems that we face in the creation of it, I've noticed a recurring pattern: we always seem to be asking ourselves, "how can we better simulate ...
3
votes
1answer
54 views

Compound intelligence?

A question about swarm intelligence as a potential method of strong general AI came up recently, and yielded some useful answers and clarifications regarding the nature of swarm intelligence. But it ...
1
vote
0answers
55 views

Analogies and similarity

The more I think about machine learning the more I realize the importance of finding similarities by using analogies as a way of learning. If I want to categorize words into hierarchical tree this ...
4
votes
2answers
70 views

Algorithms can be greedy. What are some other algorithmic vices?

Greedy algorithms are well known, and although useful in a local context for certain problems, and even potentially find general, global optimal solutions, they nonetheless trade optimality for ...
19
votes
5answers
4k views

What are the current theories on developing a conscious AI?

Is most development or theory geared towards the idea that consciousness is an emergent phenomenon? That once we put enough complexity into our system, it will become self-aware? Or is this even a ...
1
vote
0answers
52 views

Deep Neural Network and learnable

Gold and Vapnik proved that what are learnable are only data of finite demension or set of language without infinite language, that is only algorithms with computational complexity weaker than NP or ...
3
votes
1answer
62 views

How can computers beat humans at image recognition?

For supervised learning, humans have to label the images computers use to train in the first place, so the computers will probably get wrong the images that humans get wrong. If so can computers beat ...
3
votes
1answer
227 views

At what rate could AI theoretically self-improve?

Due to recursive self-improvement, AI could lead to an intelligence explosion improving on itself year over year exponentially. Assuming the proper environment was created to allow an AI to self-...
6
votes
3answers
179 views

Has it been theoretically proven or dis-proven that a machine can generally think and communicate on its own?

I am not looking for proof of AI (too broad, I know) concepts trying to solve a specific business problem, instead for a proof (or dis-proof) or a model (or a source of the same) where a machine is ...
3
votes
2answers
266 views

Are Dreams a Form of Backpropagation?

Humans often dream of random events that occurred during the day. Could the reason for this be that our brains are backpropagating errors while we sleep, and we see the result of these ...
-2
votes
3answers
148 views
-6
votes
5answers
156 views

Is it possible for an AI to work in a computer without the power cord being plugged in?

Could an Artificial Intelligence be able to interact (see, talk, etc.) with someone even when there's no power cord connected to the machine it's running on? Might it find some way to generate its own ...