A tool for ML professionals striving for clarity — Machine Learning Engineers always want more information. So, being able to explain machine learning models is an ongoing challenge to people like us. Among the various methodologies developed to explain a model’s decisions, Shapley Values stand out due to their robust theoretical foundation and increasing practical applications. What are Shapley Values?

Grid Search vs Random Search, which one for Deep Learning models? — Sometimes, I wish that creating a deep learning model was as simple as it was for Myke Tyson to win his boxing match es— one punch and it is over. The truth is, I often find myself asking too many questions when I start optimizing my models: How many layers…

The top 10 techniques to get started — Whenever I am teaching Deep Learning, students find its data preprocessing a bit complex, but it’s understandable. Unlike traditional machine learning models, deep learning algorithms often require data to be in very specific formats. …

From Skepticism to Acceptance — A couple of months ago, I was working on a biomedical project that involved using deep learning to predict the need to further diagnose a patient with mental illness. …

Creating more dynamic interactions using machine learning — As a machine learning engineer and a gamer it is inevitable to wonder how video games will evolve in the next few years after, especially after the launch of ChatGPT and Midjourney. …

Techniques and trade-offs to keep in mind — Class imbalance is a common challenge in machine learning and deep learning. What is it? It’s the situations where the classes in the target variable are not represented equally. …

Increase automation and communication in machine learning projects — One of the questions I got asked by interviewers when transitioning from a data scientist role to a machine learning (ML) engineer was: “How comfortable are you with the CI/CD process? Could you explain to me what it is and why it’s important?”. The problem in answering their question is…

Catch errors early on in the development process — Have you ever been to a data scientist or machine learning engineer interview and was asked about how to setup a unit tests? If you have no idea of what I am talking about or just want to refresh the basics of unit test, then this post is for you. …

Understand their strengths and weaknesses, so you can make the most out of each algorithm. — As a machine learning professional, one of the most common tasks you will be asked to do is building a recommending system. A recommending system is a type of algorithm that suggests items to users based on their past behaviour and preferences. …