Bayesian

An intuitive explanation on updating your beliefs using Bayes’ theoremPhoto by Dylan Clifton on UnsplashIn my previous article we derived Bayes’ theorem from conditional probability. If you are unfamiliar with Bayes’ theorem, I highly recommend reading that article before carrying on with this one:In this article we will use Bayes’ theorem to update our belief and show how with more data we become more certain of our hypothesis.We can write Bayes’ theorem as follows:Equation generated in LaTeX by author.P(H) is the…

Know the differences and learn when to use themPhoto by Lucas Santos on UnsplashFrequentist and Bayesian methods both have statistical inference in machine learning algorithms. Generally, the machine learning algorithms that we use commonly like linear and logistic regression show statistical inference using the frequentist method. However, the Bayesian method could also be applied in algorithms, for instance — Bayesian neural networks.The method of choice depends on the problem at hand and the data, which we will discuss…

Leverage Bayesian Theory to boost your performancePhoto by Syarafina Yusof on UnsplashIn a previous post, we presented a case study about Image Classification using Tensorflow and Deep Learning Methods.Although the case study was minimal, it showcased every stage of a machine learning project: Cleaning, preprocessing, model building, training, and evaluation. But we skipped tuning.In this article, we will delve a little deeper into hyperparameter optimization. Again, we will use the Fashion MNIST dataset, which is…

A math + code introduction to Bayesian Inference methods — Markov Chain Monte Carlo and Variational Inference.Photo by Scott Graham on UnsplashIn the previous blog post, I gave an introduction to the world of Bayesian Statistics. It examined how Bayesian statistics presents a way to incorporate evidence into our model to obtain a better model. This process is known as inference, which is fancy mathematical speak for obtaining/approximating the posterior.However, one big issue with Bayesian statistics is that finding…