15

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 a little. Depending on the quality of the PRNG, the problem ranges from easy to almost impossible. A very weak PRNG like the one XKCD published could of course ...


4

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 an example. Here is the final code without detailed explanation, still quite simple and useful in case the link goes offline: from random import randint from ...


3

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 with 20% chance of correct, the security of the entire world would be vulnerable to attacks, as things ranges from cryptocurrency and secure data transfer is all ...


3

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 which demonstrates utility, then no. (For instance, Nimatron, potentially the first functioning AI, beat most human competitors at NIM. But Nimatron was ...


3

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 numbers out of 90. Trained a MLP classifier with training data composed as follow: ith sample : X <- lotteryResults[i:i+100], Y <- lotteryResults[i] In ...


3

If a pseudorandom number generator is throwing out numbers, then, in the analysis of these numbers, you will be able to determine the algorithm that produced them, because the numbers aren't random; they are determined by that algorithm and not by chance. If the world is made up of physical laws that are able to be understood and replicated, then the ...


3

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 computing is involving logic, as boolean logic drives any processing. Linguistic logic, where there is a logic in the sequencing of sentences within a text. A ...


3

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 with generally greater than 0 uncertainty. Depending on who you talk to, we live in a random universe (the way we define quantum mechanics depends on a wave ...


2

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 this is the previous few sequences of characters generated: (Just an example, for the practical use larger range, is used) lwjVJA Ls3Ajg xpKr+A XleXYg 9hyCzA ...


2

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 adding numbers, there already exist many strong pseudo-random and "true" random sources, possible without using any AI approach, and demonstrably good enough for ...


2

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 layered NN. Since with different initial values the 3 layer NN might perform better. You could run multiple times and probabilistically say that this is better, ...


1

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. This is not a technology that exists, but a goal of some AI research to perform more and more general tasks. So 'generating random value' is also a task ...


1

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 directory,make sure you set shuffle to False or if you do not then set the random seed. If you use transfer learning make that part of your network non-trainable. ...


1

There are two weight-initializing methods for neural networks: 1-Zero initializing 2-Random initializing https://towardsdatascience.com/weight-initialization-techniques-in-neural-networks-26c649eb3b78 If you choose zero initalizing method in every train loop, you may get same results OR you can use transfer learning according to your problem, it allows ...


1

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 when first learning machine learning. If the lottery is truly a random physical process with fair, i.e., balanced ping pong balls, then you cannot predict which ...


1

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 book uses some randomness in developing some side thread or some episodic character and I would say, that yes - sometimes we think up of something random. Some ...


1

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 in data then machine might consider that as pattern and behave according to that (Which will be bias for us). Generating random numbers is a different story in ...


1

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 fit in memory), working on random samples can be an optimal way to train a machine learning algorithm. One of the most used optimization technique in those cases ...


1

Previous answers are very well written. I just wanted to supplement the thread by giving a simple example. The example shows how a logical function can be computed without errors using noisy components. Taken verbatim from Neural Networks by Raul Rojas. An excellent book: an example of a network built using four units. Assume that the first three units ...


1

In certain games, random selection is the optimal strategy. See: Matching Pennies Strategy is essentially a plan of action utilized to achieve a goal. If random choice can be a strategy, it seems that it must be a form of logic, even if the nature of the stochastic process is counter to all forms of formal logic. This seems paradoxical, in that the ...


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