We can replace normal multiple regression with Bayesian Multiple Regression.
Posts by CategoryRecent Posts
Sort By Year
Overflow problems are common in neural network-like structures.
We sometimes encounter the calculation of
Sigmoid function (standard logistic function) is defined as
If the data is large, we encounter overflow in sigmoid function.
Suppose we are doing Gaussian Mixture (1D). The histogram of posterior distribution is (we choose a new from this histogram),
You may wonder why is the same as .
Natural Language Processing
Perplexity is commonly used to evaluate language models.
Log likelihood of Latent Dirichlet in Collapsed Gibbs Sampling.
This is not a smoothed LDA. The model is Beli, Ng, and Jordan (2003) Figure 1. You can find another useful derivation note.
The probability mass function of Bernoulli distribution is
We would like to minimize bugs when we write code. If we encounter errors, we know something is going wrong, but some serious bugs don’t stop the code.
Jekyll and Github Pages are great tools to create a website. I used minimal-mistakes template.
On This Page