Shane Nolan shanenolanwit

Introduction Do you often find yourself wondering what is the difference between euclidean distance and cosine distance? How many sleepless nights have you had trying to classify your books as either cat books or dog books? Do you have difficulty estimating a dogs age? Do you like vague quotes, badly phrased answers and reading python scripts? Well then my friend, if the path be beautiful, let us not ask where it leads .

I recently took the opportunity to sit the AWS Security Specialty exam, widely regarded as one of the more difficult AWS exams. To make it extra spicy on myself, I sat the exam online through Pearson Vue. So turn off the television, in fact, why don’t you turn off all the lights except for the one over your favorite chair? and we’ll talk about security here in the dim.

Clickbait Did I pass it in a week? No. In hindsight, do I think it can be passed in a week? Yes… Well, it depends. Ok whats the story Security+ validates the baseline skills necessary to perform core security functions and pursue an IT security career. I stole that definition from somewhere, but basically this certification removes the training wheels from your security bike and allows you to cycle into your next interview without your Da holding the back of your bike, and not falling flat on your face.

Intro Thanks to the combination of a pandemic and the Irish weather, I have a little bit of time to tell you all a tale today. In 1966 Abraham Maslow proposed a theory in his work The Psychology of Science, the theory known as Maslow's hammer is popularly phrased as if all you have is a hammer, everything looks like a nail and is one of the phrases I am constantly reminded of when I see people play with regular expressions (myself included).

Introduction Natural Language Generation (NLG), is a field of artificial intelligence (AI) that aims to transform data into information. It can enrich your dataset through data reduction and summarisation, or through data growth and supplementation. Imagine never having to hire an intern again. NLG adoption is rapidly increasing, primarily in the field of financial reporting, but today I will be discussing how it could potentially be utilised by chatbot technology to enrich training data sets and increase a models intent detection capabilities.

Once upon a time . . Back in the days when you could go into a shop with a pound and come out with a bag of monster munch, a can of coke, and still have a few pence left in your back pocket, most text mining applications relied on a technique known as bag-of-words. This technique basically took all the words in a given piece of text, disregarding their order, not caring about their context and used each words frequency to classify the entire document using predefined classes.

A guide for lazy financial analysts and optimistic investors If there’s any industry thats both resistant to change and the perfect target for automation, its the finance industry. NLG (Natural Language Generation) can analyse, interpret, summarise and explain large data in a fraction of the time it would take Johnny Wallstreet to do manually with his calculator and dictionary. Using an NLG engine also removes human bias and error, providing reliable, repeatable, consistent and honest results.

Happy 2021 All the way back in 2020 I had an idea in my head that I would blog about my Masters thesis, I decided I would build the blog myself and on top of all that I would learn React JS as I learned how to blog good. The end result was very few blogs, I didn’t have the time to learn how to make React make things look nice, and that made me not want to showcase any of my shit.

I had just published my first blog post on shanenolan.io, a work of art, a masterpiece some might say. I was on a bloggers high, but already looking for another fix. I recalled recently speaking with my colleague Drew about my experience with AWS exams and her ongoing experience studying for the Comptia Security+ exam. Drew had also just authored an interesting blog on bounce rates, which uses one of my favourite websites ( spacejam.

Following on from my Guide to the AWS Machine Learning Specialty I want to share this list which is based on what I feel are the most important terms and concepts to understand before tackling the ML specialty exam. You should be able to scan this list and comfortably explain and/or discuss each point. General ML Foundations Supervised / semi supervised / unsupervised / transfer / reinforcement learning Rate of Growth - Derivative v Gradient Parameters v Hyperparameters Classification v Regression Linear regression v Logistic regression Overfitting v Underfitting Know your data What is an attribute?