In this final post, we will briefly examine the strengths and weaknesses of n-gram models and explore why it may be necessary to refine them for improved predictions.
Read more

In this post, we will implement a simple n-gram model in C# using a limited corpus. This will highlight the key considerations to keep in mind when it comes to coding.
Read more

In this post, we will build on the concepts covered in the previous posts and explore how they can be applied to n-gram language models.
Read more

In this post, we will delve into the concept of probabilities, with a particular emphasis on conditional probabilities. This foundational understanding will prepare us for the next post, where we will explore n-gram language models in greater depth.
Read more

In this post, we provide a brief overview of the Google's autocomplete feature to showcase a concrete application of the concepts we are exploring.
Read more

Starting today, we launch a series of articles delving into the implementation of the Google's autocomplete feature (we will detail later what it is exactly). More broadly, our aim is to explore the n-gram language model, shedding light on how to predict and generate sentence endings based on their beginnings. Our goal …
Read more

Starting today, we initiate a series that explores neural networks and deep learning. The objective is to uncover the complexities of utilizing neural networks to accomplish tasks that elude other algorithms.
Read more

In this post, we revisit key aspects of logistic regression and highlight its limitations, thereby motivating the introduction of more powerful algorithms.
Read more

In this post, we will explore how logistic regression can handle non-linearly separable data and take a step towards automating this process.
Read more

In this post, we explore how we can naturally derive neural networks from logistic regression and enable them to automatically handle complex data configurations.
Read more