N-gram language models – Part 1

Contents1 Background2 Data3 Unigram language model3.1 What is a unigram?3.2 Training the model Background Language modeling — that is, predicting the probability of a word in a sentence — is a fundamental task in natural language processing. It is used in many NLP applications such as autocomplete, spelling correction, or text generation.   Currently, language models based on …

N-gram language models – Part 1 Read More »

Gaussian samples – Part (2)

Contents1 Background2 How does the Box-Muller transform work?3 Derivation of Box-Muller transform Background In part 1 of this project, I’ve shown how to generate Gaussian samples using the common technique of inversion sampling: First, we sample from the uniform distribution between 0 and 1 — green points in the below animation. These uniform samples represent the cumulative …

Gaussian samples – Part (2) Read More »

Gaussian samples – Part (1)

Contents1 Background2 Starting point: the uniform number generator3 Method 1: Inverse transform sampling4 How does this work? Background Gaussian sampling — that is, generating samples from a Gaussian distribution — plays an important role in many cutting-edge fields of data science, such as Gaussian process, variational autoencoder, or generative adversarial network. As a result, you often see functions …

Gaussian samples – Part (1) Read More »

Practice Design for Try/Fail Fast

Contents1 Architecture2 Continues Integration and Continues Deployment At the moment, AI/ML/DL are hot keywords in the trend of Software development. The world have more successful projects based on AI technologies such as Google Translate, AWS Alexa, …AI makes machine smarter than. So, the way from idea to successfully have many challenges if want to make …

Practice Design for Try/Fail Fast Read More »

Duality theorems

Contents1 Introduction2 Linear programming2.1 Definition3 Geometric interpretation of a linear program4 Hiring Data Scientist / Engineer 5 Data Science Blog6 AI / Data Science Project7 Vietnam AI / Data Science Lab Introduction Optimization shows up everywhere in machine learning, from the ubiquitous gradient descent to quadratic programming in SVM, to expectation-maximization algorithm in Gaussian mixture models. However, one aspect of optimization that …

Duality theorems Read More »