19 votes

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

If we are talking about a perfect RNG, the answer is a clear no. It is impossible to predict a truly random number, otherwise it wouldn't be truly random. When we talk about pseudo RNG, things change ...
Demento's user avatar
  • 1,684
10 votes

How is ChatGPT able to repeat random numbers?

As well as decent modelling of purposes or strings of digits, ChatGPT can identify when a completely novel string might be a product name, a fictional person or place etc. The language model in ...
Neil Slater's user avatar
  • 32.1k
8 votes

Can you confirm that the transformer works strictly deterministically and there is no randomness inside or between the attention layers?

Can you confirm that the transformer works strictly deterministically and there is no randomness inside or between the attention layers? Of course, there is no injected randomness in a regular ...
Luca Anzalone's user avatar
6 votes
Accepted

Is true random number generation an AI concept?

As it can be easily pointed out that true random numbers cannot be generated fully by programming and some random seed is required. This is true. In fact, it is impossible to solve using software. No ...
Neil Slater's user avatar
  • 32.1k
5 votes

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

Old question, but I thought it's worth one practical answer. I happened to stumble upon it right after looking at a guide of how to build such neural network, demonstrating echo of python's randint as ...
isp-zax's user avatar
  • 159
3 votes

Can you confirm that the transformer works strictly deterministically and there is no randomness inside or between the attention layers?

That's right, the Attention Layer output is totally deterministic. The temperature parameter is related to generative tasks (note that this is not the only thing you can do with Attention and the ...
Ciodar's user avatar
  • 400
3 votes

Is the output of image generation models like Midjourney and Stable Diffusion deterministic?

Yes. By setting the seed you can control the reproducibility. See the Guide to using seed in Stable Diffusion With all parameters fixed except for the seed, the output will have some degree of ...
Brian O'Donnell's user avatar
3 votes

Is randomness anti-logical?

I might misunderstand your question, but there seem to be different levels of logic at play here. Computing logic, whereby any computational process is based on processor logic. In this case, any ...
Oliver Mason's user avatar
  • 5,387
3 votes

Is randomness anti-logical?

I think the answer here lies in that the dictionary definition of randomness you have is not the one used in statistics, ML, or mathematics. We define randomness to mean there exists a distribution ...
mshlis's user avatar
  • 2,359
3 votes

Is randomness necessary for AI?

Is randomness (either true randomness or simulated randomness) necessary for AI It depends on how you define Artificial Intelligence. If you regard it strictly as an intentionally created construct ...
DukeZhou's user avatar
  • 6,227
3 votes

Can a neural network be used to predict a sequence of integers based on dataset of previously produced random numbers?

The post you linked to clearly states that pseudo random number cannot be predicted. Their randomness is made to be nearly perfect, and if you ever found a way to even predict a pseudo random number ...
Clement's user avatar
  • 1,745
3 votes

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

Being a complete newbie in machine learning, I did this experiment (using Scikit-learn ): Generated a large number (N) of pseudo-random extractions, using python random.choices function to select N ...
Francesco Bochicchio's user avatar
2 votes

Is true random number generation an AI concept?

Such a great question. I would concur with Dennis Soemers comment that humans are not great at thinking of random numbers (just think about any card trick). However, we are very good at creating ...
benbyford's user avatar
  • 348
2 votes

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

Adding to what Demento said, the extent of randomness in the Random Number Generation Algorithm is the key issue. Following are some designs that can make the RNG weak: Concealed Sequences Suppose ...
Ugnes's user avatar
  • 2,023
2 votes

Is randomness necessary for AI?

Yes, randomness is necessary to achieve generality in theory. Right now AIs we have are on the basis of seeking pattern and use them to predict future moves or outcomes. If we don't include randomness ...
Rajat Paliwal's user avatar
2 votes

Why AI is (or not) a good option for the generation of random numbers?

Why AI is (or not) a good option for the generation of random numbers? AI approaches are generally not good for generating random numbers, for these reasons: Similar to why they are not good for ...
Neil Slater's user avatar
  • 32.1k
2 votes

How to deal with random weights initialization in hyperparameters tuning?

I don't think you can. Say a NN with 3 layers gives an accuracy of 95.3% and another NN with 4 layers gives an accuracy of 95.4%. Then there is no guarantee that the 4 layer NN is better than the 3 ...
codeblooded's user avatar
2 votes

Is whisper.ai non-deterministic?

Yes, you can see a comment from discussion here: https://github.com/openai/whisper/discussions/81 This happens when the model is unsure about the output (according to the compression_ratio_threshold ...
MikeL's user avatar
  • 121
2 votes

How is ChatGPT able to repeat random numbers?

Existing answer is great about model generalization, but I would like to add about an important inductive bias of the Transformer model architecture used for ChatGPT. In the Transformer model ...
pcpthm's user avatar
  • 266
2 votes

Can you confirm that the transformer works strictly deterministically and there is no randomness inside or between the attention layers?

The other answers might be correct for the mathematical abstraction of a GPT-like model, but are false for the actual real-world models. On-device forward passes through any big quantized neural ...
Daniel Paleka's user avatar
1 vote

Is the output of image generation models like Midjourney and Stable Diffusion deterministic?

Even with all parameters fixed, I have gotten slightly different results with SD 1.4 at least when generating a batch of images. I haven't done extensive testing on this, but even a single sample is ...
NikoNyrh's user avatar
  • 767
1 vote
Accepted

Clustering by using Locality sensitive hashing *after* Random projection

I think the following is the way to look at your question. RP reduces dimensionality based on distance. LSH clusters data based on a similar distance method used in RP. The primary function of any ...
Arun Aniyan's user avatar
1 vote

Can AlphaZero develop significantly different playing styles (depending on the random games from which it learrns)?

The primary questions They only trained AlphaZero once, and then let it play against itself. So yes, both players are identical. MCTS as implemented by AlphaZero does not intentionally use any ...
KarelPeeters's user avatar
1 vote
Accepted

How does randomization avoid entering infinite loops in the vacuum cleaner problem?

how does randomization (for instance flipping a fair coin) avoid entering the infinite loop? The coin is flipped on each occasion that a decision is required (as opposed to once in order to define ...
Neil Slater's user avatar
  • 32.1k
1 vote
Accepted

Random value generator using a single neuron or DNN

AI is supposed to do anything human or traditional computer can do, that is what we expect AI to be. Technically you would need AGI (Artifical General Intelligence) to do anything a human can do. ...
Neil Slater's user avatar
  • 32.1k
1 vote

How to deal with random weights initialization in hyperparameters tuning?

There are other sources that will lead to different results in addition to weight initialization. For example dropout layers. Make sure you specify the random seed.Also data reading using flow from ...
Gerry P's user avatar
  • 714
1 vote

How to deal with random weights initialization in hyperparameters tuning?

There are two weight-initializing methods for neural networks: 1-Zero initializing 2-Random initializing https://towardsdatascience.com/weight-initialization-techniques-in-neural-networks-...
Barış Akın's user avatar
1 vote

Can a neural network be used to predict a sequence of integers based on dataset of previously produced random numbers?

If is a truly a random number, and you could guess each of the next successive five in sequence, then you could win the lottery consistently. This is one of the first tasks many people try to do ...
rich4piano's user avatar
1 vote

Is randomness necessary for AI?

It might be too philosophical answer, but maybe first we need to answer the question whether a human way of thinking or his creativeness includes random elements. For example if an author writing a ...
GKozinski's user avatar
  • 1,260
1 vote

Is randomness anti-logical?

Let me add an example from machine learning that shows that resorting to randomness is the optimal way, sometimes. When working on the whole data is not tractable (computation cost, data does not ...
naive's user avatar
  • 699

Only top scored, non community-wiki answers of a minimum length are eligible