Oreolorun is a machine learning engineer with particular interest in computer vision applications. He loves to write about nuanced concepts in machine learning in an easy to understand manner.
In this article, we explore concepts related to convolutional neural network architectures with the intention of building our understanding enough to create and understand the capabilities of an AlexNet model, from scratch.
In this article, we take a look at 1 x 1 convolution not only as a down-sampling tool, but also its many other potential uses with convolutional neural networks, such as dimensionality reduction or adding non-linearity.
This blog details about Filters in Convolutional Neural Networks (CNNs) and how they are crucial for detecting patterns within input data. These filters, or kernels, slide over the input image to perform convolutions.
In this article, we explore how and why we use padding in CNNs in computer vision tasks. We'll then jump into a full coding demo showing the utility of padding.
