Questions tagged [random-variable]
For questions related to the mathematical concept of a random variable (in the context of AI).
8
questions
1
vote
0answers
23 views
What machine learning model should I use for a random dice-based game?
Consider a game like Pig (https://en.wikipedia.org/wiki/Pig_(dice_game)), but with a few additions: namely functions of both player's score and turn number that have unique impacts on scoring.
What ...
1
vote
1answer
53 views
In the definition of the state-action value function, what is the random variable we take the expectation of?
I know that
$$\mathbb{E}[g(X) \mid A] = \sum\limits_{x} g(x) p_{X \mid A}(x)$$
for any random variable $X$.
Now, consider the following expression.
$$\mathbb{E}_{\pi} \left[ \sum \limits_{k=0}^{\infty}...
3
votes
1answer
104 views
What does the notation $\mathcal{N}(z; \mu, \sigma)$ stand for in statistics?
I know that the notation $\mathcal{N}(\mu, \sigma)$ stands for a normal distribution.
But I'm reading the book "An Introduction to Variational Autoencoders" and in it, there is this notation:...
1
vote
1answer
35 views
Why is this variable in equation 2 of the SQAIR paper a random vector of $n$ ones followed by a zero?
I've been reading the SQAIR paper lately, and the mathematics involved seems a bit complicated.
Some background, about the paper: SQAIR stands for Sequential Attend, Infer, Repeat - the paper does ...
0
votes
1answer
51 views
Should the biases be zero or randomly initialised?
I'm initialising DNN of shape [2 inputs, 2 hiddens, 1 output] with these weights and biases:
...
1
vote
0answers
45 views
What is the point of converting conditional probability to factor for Variable Elimination?
I have this slide from my AI class on using a Bayes network to compute a conditional probability. I don't really understand the point of converting the conditional probabilities to factors (besides ...
4
votes
1answer
139 views
Is learning possible without random thoughts and actions?
In my view intelligence begins once the thoughts/actions are logical rather than purely randomn based. The learning environments can be random but the logic seems to obey some elusive rules. There is ...
2
votes
0answers
54 views
What kind of distributions can be used to model discrete latent variables?
If we take the vanilla variational auto-encoder (VAE), we $p(z)$ is a Gaussian distribution with zero mean and unit variance and we approximate $p(z|x) \approx q(z|x)$ to be a Gaussian distribution as ...
