Matrix loaders for some non-uniform matrix distributions

[darthnoward]

as per chatgpt, some common non-uniform distributions include:

Normal Distribution: The normal distribution is frequently used in ML/DL algorithms for tasks such as regression, generative modeling (e.g., Gaussian mixture models), and anomaly detection. It is also a fundamental assumption in many statistical techniques, such as linear regression and Gaussian processes.
Exponential Distribution: The exponential distribution can be employed in ML/DL algorithms for survival analysis, time-to-event modeling, and reinforcement learning. It is often used to model the duration between events or time steps.
Binomial Distribution: The binomial distribution is utilized in ML/DL algorithms for classification tasks, especially in models that involve binary outcomes or binary classification.
Poisson Distribution: The Poisson distribution is used in ML/DL algorithms for count data modeling, such as in natural language processing (NLP) for text classification, topic modeling, and sentiment analysis.
Beta Distribution: The beta distribution finds applications in ML/DL algorithms for tasks that involve modeling probabilities or proportions, such as Bayesian inference, Bayesian optimization, and click-through rate (CTR) prediction.