Oct 4, 2025 · 8 min read · Welcome back, fellow data adventurers! So far in our "From Zero to Neuron" series, you've built neural networks to classify handwritten digits and predict house prices. You've seen the raw power of these models when trained from scratch. But here’s a...
Join discussion
Dec 17, 2024 · 2 min read · Today, I discovered that the sigmoid function is equivalent to softmax when applied to two inputs, with one input fixed to zero. With almost a decade of experience in machine learning, and earlier work in compute for signal processing, I had never co...
Join discussionNov 10, 2024 · 3 min read · In a neural network, an activation function decides if a neuron should be activated based on the sum of its inputs and weights. This process adds non-linearity to the network, allowing it to learn from non-linear data and solve complex problems like ...
Join discussion
Sep 16, 2024 · 11 min read · What is Classification? When it comes to Machine Learning, the 2 most commonly used algorithms are Linear and Logistic Regression. In this article I'm going to explain the second most commonly used machine learning algorithm - Logistic Regression. In...
Join discussion
Jan 14, 2024 · 3 min read · Neural networks, the cornerstone of artificial intelligence, operate as interconnected systems inspired by the human brain. Let's delve into the key components of neural networks, understand their roles, challenges, and explore their wide-ranging app...
Join discussion
Jul 13, 2023 · 7 min read · In the realm of machine learning and statistical modeling, logistic regression is a powerful algorithm used for binary classification problems. It allows us to predict the probability of an event occurring based on a set of input variables. Whether y...
MMMA commented
Sep 11, 2021 · 3 min read · Let’s start with the basics—what exactly is the sigmoid function? The sigmoid function is a mathematical function commonly used in machine learning, especially in binary classification problems and neural networks. It’s defined by the formula: When ...
Join discussion