To reiterate from the Neural Networks Learn Hub article, neural networks are a subset of machine learning, and they are at the heart of deep learning algorithms. They are comprised of node layers, containing an input layer, one or more hidden layers, and an output layer. Each node connects to another and has an associated weight and threshold. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data is passed along to the next layer of the network.

While we primarily…


Recommender System is a system that seeks to predict or filter preferences according to the user’s choices. Recommender systems are utilized in a variety of areas including movies, music, news, books, research articles, search queries, social tags, and products in general.

Recommender systems produce a list of recommendations in any of the two ways –

  • Collaborative filtering: Collaborative filtering approaches build a model from user’s past behavior (i.e. items purchased or searched by the user) as well as similar decisions made by other users. …

The ability for computers to use analyze images is incredible, but at the same time it is limited the same way humans might also classify things. We first need to know what is happening when we ask a computer to “look” at an image, and then we need to see the different ways that

Firstly, deep learning nearly always requires a large amount of annotated data. This biases vision researchers to work on tasks where annotation is easy instead of tasks that are important.

There are methods which reduce the need for supervision, including transfer learning, few-shot learning, unsupervised learning…


Whenever we want to setup a specific project we need to make sure the setup is structured such that it is intuitive and it feed in to other directories properly. At the moment I am starting a brand new project with friends and it is important to make sure that when setting it up, the project adheres to rules and structures that make it easy to reproduce and export.

The first thing you will have in your initial package of functions, models, and classes is an __init__.py, which is used to import the directory as a package and you don’t…


Every signature is a little different. There are flourishes and tendencies when coding that point to something akin to a signature, this can be both helpful and not. But by and large the rules one might take when starting to code often manifest themselves in the code that is presented to us, and we take it as the standard (to a degree). What PEP-8 does is establish guidelines that are helpful when trying to code, such as how to name classes or handle indents. An appealing set of code can distinguish yourself from others and help you understand what your…


Imagine trying to learn a language where you are learning either all of the words or understanding the intricacies of grammar before diving into the words. It could in theory work, but it doesn’t make much sense when it comes to how the world works when we are taught. The words and grammar come in parallel, complimenting each other, and helping to establish a bridge to more complex or detailed words and structure. In a lot of ways dealing with code is not too different. We have much of the lexicon and understand (sometimes) how to apply it for the…


During some downtime before an exam when I was a young chemistry student in college I asked my professor at the time “We are learning how to understand the chemical world around us, and all of the powers that come along with that knowledge, but how come there is no instruction about the ethics and how to properly use that knowledge? I hope that everyone here will use their skills to better humanity, but why is that taken as a given?”. In front of the 150 other students in the room, he said “Frankly we should. …


The curse of dimensionality is where the feature spaces increases and as a result the volume of the space increases so fast that the available data become sparse, and therefore the error increases too. When we first learn about dimensions as kids we are told there are 3 dimensions. For those that take hard sciences or dig a little deeper, there are at least 4 dimensions, sometimes up to 11 or 26 (depending on your comfort with modern String Theory). …


“Bad” data is the main nemesis of many data scientists. Being able to outwit and outmaneuver their various slings and arrows is what I think drives many to engage with Data Science as it is akin to solving a puzzle. But like any puzzle an approach and understanding of how to beat it is important, starting with the corners of a jig-saw puzzle or matching groups of colors on a Rubik's cube.

The issue I want to engage with here is data found in the fringes of the data set. I want to handle data that is close to zero…


This blog is for those that are frustrated when approaching nested data. It is my hope that this will help you access the data you need. I am writing this assuming that you at least know what dictionaries and lists are, and are familiar with some of the methods attached to them like .items() for dictionaries and .append() for lists. This is important for working with web scrapping, pulling data from website API’s, job interview questions, or just basic data structures.

When I say periscoping I am referring to the idea that while you are in a vast sea of…

Guymonahan

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store