Dimensionality Reduction

Dimensionality Reduction is a powerful technique that is widely used in data analytics and data science to help visualize data, select good features, and to train models efficiently. We use dimensionality reduction to take higher-dimensional data and represent it in a lower dimension. We’ll discuss some of the most popular types of dimensionality reduction, such … Read more

Recurrent Neural Networks for Language Modeling

Many neural network models, such as plain artificial neural networks or convolutional neural networks, perform really well on a wide range of data sets. They’re being used in mathematics, physics, medicine, biology, zoology, finance, and many other fields. However, there is one major flaw: they require fixed-size inputs! The inputs to a plain neural network … Read more

All About Autoencoders

Data compression is a big topic that’s used in computer vision, computer networks, computer architecture, and many other fields. The point of data compression is to convert our input into a smaller representation that we recreate, to a degree of quality. This smaller representation is what would be passed around, and, when anyone needed the original, they … Read more

A Guide to Improving Deep Learning’s Performance

Although deep learning has great potential to produce fantastic results, we can’t simply leave everything to the learning algorithm! In other words, we can’t treat the model as some black-box, closed entity that can read our minds and perform the best! We have to be involved in the training and design process to make sure … Read more

Introduction to Convolutional Neural Networks for Vision Tasks

Neural networks have been used for a wide variety of tasks across different fields. But what about image-based tasks? We’d like to do everything we could with a regular neural network, but we want to explicitly treat the inputs as images. We’ll discuss a special kind of neural network called a Convolutional Neural Network (CNN) that … Read more

Complete Guide to Deep Neural Networks – Part 2

Read Part 1 here. Last time, we formulated our multilayer perceptron and discussed gradient descent, which told us to update our parameters in the opposite direction of the gradient. Now we’re going to mention a few improvements on gradient descent and discuss the backpropagation algorithm that will compute the gradients of the cost function so … Read more

Complete Guide to Deep Neural Networks – Part 1

Neural networks have been around for decades, but recent success stems from our ability to successfully train them with many hidden layers. We’ll be opening up the black-box that is deep neural networks and looking at several important algorithms necessary for understanding how they work. To solidify our understanding, we’ll code a deep neural network … Read more

Building Blocks – Data Science and Linear Regression

“Data science” or “Big data analyst” is a phrase that has been tossed around since the advent of Big Data. But what is it, really? Well imagine working for a retail company. One of the questions you may be asked to answer is “how many chips should we stock up for this month?” It seems … Read more

Overview of Machine Learning

Computers are incredibly dumb. They have to be told explicitly what to do in the form of programs. Programs have to account for every possible branch of logic and are specific to the task at hand. If there are any anomalies in the set of inputs, a program might not produce the right output or … Read more