Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Most Popular

more tags
1500 questions
40
votes
4 answers

What is the concept of the technological singularity?

I've heard the idea of the technological singularity, what is it and how does it relate to Artificial Intelligence? Is this the theoretical point where Artificial Intelligence machines have progressed to the point where they grow and learn on their…
WilliamKF
  • 2,513
  • 1
  • 25
  • 31
40
votes
6 answers

Is the Turing Test, or any of its variants, a reliable test of artificial intelligence?

The Turing Test was the first test of artificial intelligence and is now a bit outdated. The Total Turing Test aims to be a more modern test which requires a much more sophisticated system. What techniques can we use to identify an artificial…
Rob Murray
  • 501
  • 5
  • 8
39
votes
7 answers

Is the "Chinese room" an explanation of how ChatGPT works?

Sorry if this question makes no sense. I'm a software developer but know very little about AI. Quite a while ago, I read about the Chinese room, and the person inside who has had a lot of training/instructions how to combine symbols, and, as a…
Guntram Blohm
  • 501
  • 1
  • 3
  • 7
39
votes
3 answers

Why is Lisp such a good language for AI?

I've heard before from computer scientists and from researchers in the area of AI that that Lisp is a good language for research and development in artificial intelligence. Does this still apply, with the proliferation of neural networks and deep…
Alecto Irene Perez
  • 599
  • 1
  • 6
  • 10
38
votes
5 answers

What is the difference between latent and embedding spaces?

In general, the word "latent" means "hidden" and "to embed" means "to incorporate". In machine learning, the expressions "hidden (or latent) space" and "embedding space" occur in several contexts. More specifically, an embedding can refer to a…
nbro
  • 40,472
  • 12
  • 105
  • 192
37
votes
6 answers

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document. I want the CNN to report errors, so I set a threshold of 90% certainty below which my…
Alexander Soare
  • 1,339
  • 2
  • 11
  • 27
36
votes
1 answer

Meaning of roles in the API of GPT-4/ChatGPT (system/user/assistant)

In the API of GPT-4 and ChatGPT, the prompt for a chat conversation is a list of messages, each marked as one of three roles: system, user or assistant.* I understand which information this represents - but what does the model with that…
Volker Siegel
  • 717
  • 1
  • 6
  • 17
36
votes
1 answer

What is the "temperature" in the GPT models?

What does the temperature parameter mean when talking about the GPT models? I know that a higher temperature value means more randomness, but I want to know how randomness is introduced. Does temperature mean we add noise to the weights/activations…
Tom Dörr
  • 483
  • 1
  • 4
  • 7
36
votes
2 answers

How can Transformers handle arbitrary length input?

The transformer, introduced in the paper Attention Is All You Need, is a popular new neural network architecture that is commonly viewed as an alternative to recurrent neural networks, like LSTMs and GRUs. However, having gone through the paper, as…
chessprogrammer
  • 2,890
  • 2
  • 15
  • 26
36
votes
7 answers

What are examples of promising AI/ML techniques that are computationally intractable?

To produce tangible results in the field of AI/ML, one must take theoretical results under the lens of computational complexity. Indeed, minimax effectively solves any two-person "board game" with win/loss conditions, but the algorithm quickly…
k.c. sayz 'k.c sayz'
  • 2,091
  • 10
  • 26
35
votes
6 answers

Is it possible to train the neural network to solve math equations?

I'm aware that neural networks are probably not designed to do that, however asking hypothetically, is it possible to train the deep neural network (or similar) to solve math equations? So given the 3 inputs: 1st number, operator sign represented by…
kenorb
  • 10,483
  • 3
  • 44
  • 94
35
votes
8 answers

Is a switch from R to Python worth it?

I just finished a 1-year Data Science master's program where we were taught R. I found that Python is more popular and has a larger community in AI. What are the advantages that Python may have over R in terms of features applicable to the field of…
ItsMeMario
  • 503
  • 1
  • 4
  • 6
34
votes
6 answers

How does an AI like ChatGPT answer a question in a subject which it may not know?

After seeing StackOverflow's banning of ChatGPT, I explored it out of curiosity. It's marvellous as it can write code by itself! Later to check if it knows chess as well like Google-Deepmind's AlphaZero AI, I asked below questions: Me: Does openai…
iammilind
  • 443
  • 1
  • 3
  • 9
33
votes
5 answers

How can I deal with images of variable dimensions when doing image segmentation?

I'm facing the problem of having images of different dimensions as inputs in a segmentation task. Note that the images do not even have the same aspect ratio. One common approach that I found in general in deep learning is to crop the images, as it…
MattSt
  • 597
  • 1
  • 5
  • 12
33
votes
4 answers

How to find the optimal number of neurons per layer?

When you're writing your algorithm, how do you know how many neurons you need per single layer? Are there any methods for finding the optimal number of them, or is it a rule of thumb?
kenorb
  • 10,483
  • 3
  • 44
  • 94
1 2
3
…
99 100