sp

In the last post, I gave a relatively simple introduction and model for a perceptron. I feel like I didn’t explain the algebraic definition quite well, so here’s what I would like to add: The multiplication in the algebraic representation of a perceptron is the dot product. It is defined as the sum of the products of each element: $$ a \cdot b = \sum_i a_i b_i $$ Now that we’ve clarified that, here’s my question from the last post: “How do we actually obtain a useful weights vector \(w\) and a bias \(b\)?”

Hello! This is the first part of a relatively introductory series to Machine Learning/Artificial Intelligence, as well as the first part of the “Perceptron” subseries. Today, I’d like to cover how a very basic Perceptron, or an artificial neuron works. They’re the building blocks of neural networks and play a significant role in the development of AI.

This is the first time since a long time that I’ve revamped my website, and personally, I really like the new theme (seems likely considering I designed it myself!).

I got an assignment for this week: write the K-Means algorithm, in any language you like. So, first, we have to understand what it does and how it works. What is K-Means? k-means clustering is a method of vector quantization, originally from signal processing, that aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean (cluster centers or cluster centroid), serving as a prototype of the cluster. [1]