A Brief Experiment — Abstract I demonstrate transfer learning by building a CNN to classify the CIFAR 10 dataset. My architecture consists of DenseNet-121 trained on ImageNet, followed by two dense layers. I achieve over 87% accuracy after 10 epochs. Introduction A key prerequisite to achieving a highly accurate neural network is a large amount of…

Introduction In 2012, Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, three researchers at the University of Toronto, achieved record-breaking performance on a prominent image classification challenge. The challenge was the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC), an annual competition in which contenders aim to achieve the most accurate classification of…

How to prevent a neural network from getting so good it’s bad. — A sufficiently complex neural network can result in ~100% accuracy on the data it was trained with, but significant error on unfamiliar/validation data. When this occurs, the network is overfitting the training data. This means that it makes predictions that are too strongly attached to features it learned in training…

What I’ve learned from my final project of Foundations at Holberton School Introduction I can’t believe my first year at Holberton School is already coming to a close. It seems like just yesterday that I didn’t know the difference between a terminal and a shell, let alone how to use them…

From the web address to your screen — So, you type in a website address and press Enter. Shortly after, a webpage appears on your screen. How exactly did that happen? In the moments after you pressed Enter, there’s actually a lot happening behind the scenes. …

A comprehensive overview of the Internet of Things What is IoT? “The Internet of Things (IoT) is the billions of physical devices around the world that are now connected to the internet, all collecting and sharing data.”¹ — IBM, Internet of Things on IBM Cloud While the precise definition depends on who you…

Because pictures are worth a thousand words — Recursion is the process of a function calling itself. It creates a loop between the start of the function and any line which contains a recursive call. To avoid an infinite loop, the function needs a base case which terminates the function. …

What every beginner must know about Python objects — Introduction: Everything is an Object Python is an object-oriented programming language. Every data structure in Python is considered an object. All objects belong to a class, which is like a blueprint for an object. It defines the object, specifying what information that object needs in order to exist, what data it will contain, what behaviors…

When programming, libraries are useful because they combine functions into a single location that can be referenced by future projects. They contain object code, so they only need to be linked. Libraries package a collection of object files into a single file and contain a symbol table used to lookup…