Improving your Machine Learning Experience

Photo by Daniel Chekalov on Unsplash

When approaching a new Machine Learning problem, there is no way of knowing from the beginning what the solution would be unless a variety of different experiments are tried and tested. Over time, practitioners have implemented a variety of different techniques to see what has worked and what has not on the majority of Machine Learning projects. From this, we have been able to generate a set of best practices when performing the Feature Engineering step within a Machine Learning pipeline.

Mind you, each one of these best practices may or may not improve your solution for each specific problem…

Natural Language Processing Notes

Building My Own “FastFoodz ”Chatbot

Photo by Andy Kelly on Unsplash

What is Dialogflow?

Dialogflow is a cloud API designed by Google to aid in the development of Conversational agents. The Dialogflow documentation describes Dialogflow as follows:

Dialogflow is a natural language understanding platform that makes it easy to design and integrate a conversational user interface into your mobile app, web application, device, bot, interactive voice response system, and so on. Using Dialogflow, you can provide new and engaging ways for users to interact with your product [Source: Dialogflow Documentation].

I’ve made up a fictional restaurant called FastFoodz; For some more context, the FastFoodz restaurant is going to be based on one of my…

Natural Language Processing Notes

Exploring the Chatbot Taxonomy

Photo by Jeffery Ho on Unsplash

What is a Chatbot?

Instead of me defining what a Chatbot is, I’ll leave it to some trusted sources…

“A chatbot is a software application used to conduct an online chat conversation via text or text-to-speech, in lieu of providing direct contact with a live human agent” [Source: Wikipedia].

“Chatbots are interactive systems that allow users to interact in natural language. They generally interact via text but can also use speech interfaces” [Source: Vajjala et al. (2020)].

“At the most basic level, a chatbot is a computer program that simulates and processes human conversation (either written or spoken), allowing humans to interact with digital…

Ensure You’re Drawing Valid Conclusions From Data

Photo by National Cancer Institute on Unsplash

Sampling Bias is one of the most common types of biases observed in real-world scenarios. It occurs when the data used to train a model doesn’t reflect the distribution of the samples that the model will receive whilst in production.

Generally, whenever we work on Machine Learning projects, it’s vital that the correct research is done about the real proportions of various properties in the data that will be observed in a production environment.

Additionally, when we are actually working on a problem and the data set is very large, it’s usually not practical, nor necessary, to work with the…

It’s a Difficult Problem

Photo by Aarón Blanco Tejedor on Unsplash

Yesterday (Monday), I spent my evening in an outdoor Lebanese restaurant. The food was so lush, but as a data professional, I couldn't help but be plagued by what happened to me at the entrance door…

The risk of Covid-19 is still very much prominent, hence all restaurants that are opening in response to eased regulations in the UK must abide by strict precautionary measures to ensure we are as safe as possible.

At the particular restaurant I attended, the safety measures included a facial recognition system that records your presence at the restaurant and measures your temperature for early…

Challenges That Occur When Working With Data

Photo by Kelly Sikkema on Unsplash

Data is central to our work as Data professionals, however, data very rarely comes prepared for us to begin waving our so-called “magic wand”; There will be problems with our data and the best way to ensure we are getting the best out of our data projects is to know what they are so that we could come up with ways to work around them.

Let’s explore some of these problems…

#1 Data Collection and Labeling

Data collection can be extremely expensive with respect to time and money in some cases — this typically occurs when we have a custom problem that doesn’t have data…

Natural Language Processing Notes

Ways To Grow Your NLP Dataset

Photo by Maxim Hopman on Unsplash

The beginning — well after the business problem has been determined — of a generic Machine Learning or Natural Language Processing pipeline consist of the Data Acquisition phase. In the Data acquisition phase, practitioners are faced with the challenge of identifying the sampling signals that measure the real-world physical conditions so that this data could be converted into digital numeric values which could be consumed by a computer.

If data is readily available then this step could be skipped — this is rarely the case in the real world. It’s essential we know of a set of techniques to improve…


Focus On What Matters

Photo by Aron Visuals on Unsplash

To someone that reads my articles regularly, you’d probably think that I’m the most contradicting person on the planet. I don’t blame you.

I recently noticed during spoken or written interactions with people, I make a multitude of assumptions about the person(s) I am communicating with. I don’t explicitly define very important aspects before stating exactly what I am saying which, depending on the context, has the potential to dilute the actual message I wish to put across.

Recently, I wrote an article about how we could simplify the initial stages of breaking into Data Science by networking. In response…

How I Got My First Data Related Job Without A Degree or Prior Experience

Photo by Karsten Würth on Unsplash

Course Complete, NOW I’m ready!

Relearn Linear Algebra — CHECK.

Relearn Statistics — CHECK.

Relearn Calculus — CHECK.

Learn Python — CHECK.

Take Andrew Ng Machine Learning course on Coursera — CHECK.

Complete a portfolio project — CHECK.


We were 4 months into 2019, and I was finally ready to make the leap from the postroom into the world of data. …

Different Ways to Aquire Data

Photo by Clay Banks on Unsplash

Without Data, we can definitely forget about doing the Science part. Yet, it amazes me how little we speak of data — Don’t worry, I am not pointing the finger. I’m guilty too; Data is at the heart of everything we do as Data Scientists, but it’s not as fun as talking about how BERT is pushing the boundaries for natural language processing (NLP) tasks, or whatever the new state-of-the-art (SOTA) architecture is.

This inherent FOMO (Fear of missing out) of what’s to come in Artificial Intelligence (AI) and Data Science is similar to the thing that has so many…

Kurtis Pykes

AI Enthusiasts with writings covering AI, Data Science, and Freelancing

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