Questions tagged [theory]

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

Filter by
Sorted by
Tagged with
52
votes
4answers
14k 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 ...
25
votes
4answers
5k views

What are the current theories on the development of a conscious AI?

What are the current theories on the development of a conscious AI? Is anyone even trying to develop a conscious AI? Is it possible that consciousness is an emergent phenomenon, that is, once we put ...
15
votes
2answers
668 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 ...
12
votes
4answers
566 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 (...
12
votes
3answers
164 views

Is there a way to understand neural networks without using the concept of brain?

Is there a way to understand, for instance, a multi-layered perceptron without hand-waving about them being similar to brains etc? For example: it is obvious that what a perceptron does is ...
11
votes
3answers
293 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 ...
11
votes
1answer
740 views

Are Cellular Neural Networks one type of Neural Networks?

I am researching Cellular Neural Networks and have already read Chua's two articles (1988). In cellular neural networks, a cell is only in relation with its neighbors. So its is easy to use it for ...
10
votes
2answers
5k views

What is the difference between goal-based and utility-based agents?

What is the difference between goal-based and utility-based agents? Please, provide a real-world example.
8
votes
4answers
312 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 ...
7
votes
1answer
3k views

What is the relationship between gradient accumulation and batch size?

I am currently training some models using gradient accumulation since the model batches do not fit in GPU memory. Since I am using gradient accumulation, I had to tweak the training configuration a ...
7
votes
2answers
138 views

What does learning mean?

Can someone explain what is the process of learning? What does it mean to learn something?
7
votes
3answers
130 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 ...
7
votes
2answers
159 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 ...
6
votes
9answers
1k 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, ...
6
votes
3answers
146 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 ...
6
votes
2answers
6k views

What is convergence in machine learning?

I came across this answer on Quora, but it was pretty sparse. I'm looking for specific meanings in the context of machine learning, but also mathematical and economic notions of the term in general.
6
votes
2answers
667 views

How can the multiple intelligences model be incorporated into AI?

I have been wondering since a while ago about the theory of multiple intelligences and how they could fit in the field of Artificial Intelligence as a whole. We hear from time to time about Leonardo ...
6
votes
2answers
5k 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)?
5
votes
7answers
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 ...
5
votes
3answers
245 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 ...
5
votes
1answer
190 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
1answer
3k views

What is the difference between simple reflex and model-based agents?

What is the difference between simple reflex and model-based agents? What is the role of the internal state, in the case of model-based agents?
5
votes
1answer
139 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 ...
5
votes
2answers
195 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 have seen lots of examples for AI sequences or a simple "...
5
votes
2answers
80 views

Is the gradient at a layer independent of the activations of the previous layers?

Is the gradient at a layer (of a feed-forward neural network) independent of the activations of the previous layers? I read this in a paper titled Mean Field Residual Networks: On the Edge of Chaos (...
4
votes
4answers
123 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 ...
4
votes
3answers
119 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/...
4
votes
1answer
701 views

What does 'democratizing AI' exactly mean?

In my AI literature research, I often notice authors use term 'democratizing AI', especially in the AutoML area. I think I have an idea of what this means, but I would like to ask you for some more ...
4
votes
2answers
195 views

Are current AI models sufficient to achieve Artificial General Intelligence?

I read an interesting essay about how far we are from AGI. There were quite a few solid points that made me re-visit the foundation of AI today. A few interesting concepts arose: imagine that you ...
4
votes
2answers
2k 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
4
votes
2answers
625 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-...
4
votes
1answer
64 views

Is there a way to ensure that my model is able to recognize an unseen example?

My question is more theoretical than practical. Let's say that I am training my cat classifier with a dataset that I feel is pretty representative of cat images in general. But then a new breed of cat ...
3
votes
6answers
433 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
3answers
311 views

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

I think that AI perceive the world. Can an AI be sentient?
3
votes
2answers
763 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 ...
3
votes
3answers
1k views

Does artificial intelligence write its own code?

Does artificial intelligence write its own code and then execute it? If so, does it create separate functions for each purpose?
3
votes
1answer
79 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
91 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
1answer
245 views

Can NEAT produce neural networks where inputs are directly connected to outputs?

Can NEAT produce neural networks where inputs are directly (without intermediate hidden neurons) connected to outputs?
3
votes
2answers
277 views

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

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
1answer
381 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 ...
3
votes
0answers
32 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 ...
2
votes
1answer
119 views

What are the types of artificial intelligence and how are they measured? [closed]

I was reading an interesting book about the role of AI in Cybersecurity, and the author mentioned there being 3-4 types. Each one is dependent on its abilities and understanding. For example, a ‘...
2
votes
1answer
96 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% ...
2
votes
1answer
96 views

Is GPT-3 an early example of Strong AI in a Narrow setting?

In GPT-2, the large achievement was being able to generate coherent text over a long-form while maintaining context. This was very impressive but for GPT-2 to do new language tasks, it had to be ...
2
votes
1answer
173 views

What make a CNN suitable for image classification or for semantic segmentation?

I've just started with CNN and there is something that I haven't understood yet: How do you "ask" a network: "classify me these images" or "do semantic segmentation"? I think it must be something on ...
2
votes
1answer
51 views

How many ways are there to perform image segmentation?

I'm new in Artificial Intelligence and I want to do image segmentation. Searching I have found these ways Digital image processing (I have read it in this book: Digital Image Processing, 4th edition)...
2
votes
1answer
77 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
1answer
65 views

What are the known ways to test AI black boxes? [closed]

Is there any conmprehensive paper or site that describes an overview of the known black box testing techniques?
2
votes
2answers
202 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 ...