Most Popular

1500 questions
30
votes
1 answer

What is the credit assignment problem?

In reinforcement learning (RL), the credit assignment problem (CAP) seems to be an important problem. What is the CAP? Why is it relevant to RL?
nbro
  • 42,615
  • 12
  • 119
  • 217
30
votes
9 answers

What is the actual quality of machine translations?

As an AI layman, till today I am confused by the promised and achieved improvements of automated translation. My impression is: there is still a very, very far way to go. Or are there other explanations why the automated translations (offered and…
29
votes
4 answers

Why does C++ seem less widely used than Python in AI?

I just want to know why do machine learning engineers and AI programmers use languages like Python to perform AI tasks and not C++, even though C++ is technically a more powerful language than Python.
29
votes
4 answers

How could we build a neural network that is invariant to permutations of the inputs?

Given a neural network $f$ that takes as input $n$ data points: $x_1, \dots, x_n$. We say $f$ is permutation invariant if $$f(x_1 ... x_n) = f(\sigma(x_1 ... x_n))$$ for any permutation $\sigma$. How could we build such a neural network? The…
29
votes
4 answers

Can a neural network be used to predict the next pseudo random number?

Is it possible to feed a neural network the output from a random number generator and expect it learn the hashing (or generator) function, so that it can predict what will be the next generated pseudo-random number? Does something like this already…
29
votes
8 answers

Is there any research on the development of attacks against artificial intelligence systems?

Is there any research on the development of attacks against artificial intelligence systems? For example, is there a way to generate a letter "A", which every human being in this world can recognize but, if it is shown to the state-of-the-art…
29
votes
5 answers

What are the minimum requirements to call something AI?

I believe artificial intelligence (AI) term is overused nowadays. For example, people see that something is self-moving and they call it AI, even if it's on autopilot (like cars or planes) or there is some simple algorithm behind it. What are the…
kenorb
  • 10,525
  • 6
  • 45
  • 95
28
votes
2 answers

Is Prolog still used in AI?

According to Wikipedia, Prolog is a general-purpose logic programming language associated with artificial intelligence and computational linguistics. Is it still used for AI? This is based off of a question on the 2014 closed beta. The author had…
Mithical
  • 2,965
  • 5
  • 28
  • 39
28
votes
4 answers

Are Siri and Cortana AI programs?

Siri and Cortana communicate pretty much like humans. Unlike Google Now, which mainly gives us search results when asked some questions (not setting alarms or reminders), Siri and Cortana provide us with an answer, in the same way that a person…
27
votes
4 answers

Is the pattern recognition capability of CNNs limited to image processing?

Can a Convolutional Neural Network be used for pattern recognition in problem domains without image data? For example, by representing abstract data in an image-like format with spatial relations? Would that always be less efficient? This developer…
27
votes
4 answers

Why do ChatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over…
TylerDurden
  • 389
  • 1
  • 3
  • 7
27
votes
1 answer

What exactly are the "parameters" in GPT-3's 175 billion parameters and how are they chosen/generated?

When I studied neural networks, parameters were learning rate, batch size etc. But even GPT3's ArXiv paper does not mention anything about what exactly the parameters are, but gives a small hint that they might just be sentences. Even tutorial…
Nav
  • 491
  • 1
  • 5
  • 10
26
votes
2 answers

Are there other approaches to deal with variable action spaces?

This question is about Reinforcement Learning and variable action spaces for every/some states. Variable action space Let's say you have an MDP, where the number of actions varies between states (for example like in Figure 1 or Figure 2). We can…
26
votes
4 answers

What is a Dynamic Computational Graph?

Frameworks like PyTorch and TensorFlow through TensorFlow Fold support Dynamic Computational Graphs and are receiving attention from data scientists. However, there seems to be a lack of resource to aid in understanding Dynamic Computational…
Blaszard
  • 1,097
  • 4
  • 11
  • 25
26
votes
4 answers

Can the decoder in a transformer model be parallelized like the encoder?

Can the decoder in a transformer model be parallelized like the encoder? As far as I understand, the encoder has all the tokens in the sequence to compute the self-attention scores. But for a decoder, this is not possible (in both training and…