What is a Software Bill of Materials and how you can create one — The software bill of materials has been a very hot topic recently with most big companies nowadays integrating it into their workflow. …

Maximizing reward is the secret sauce to artificial intelligence — This paper proposes an intriguing hypothesis that incentivizing AI agents with reward is enough to achieve General Artificial Intelligence. The paper is more of a philosophical paper rather than one with a machine learning model and code. I guess this gives us an indication of why Deep Mind has been…

Microsoft’s competitive model for training huge models (compared to Google Switch Transformers and OpenAI GPT-3) — It can train models with over 13 billion parameters on a single GPU, a 10x increase in size compared to popular framework such as PyTorch, and it does so without requiring any model change from the data scientists or sacrificing computational efficiency. Source: Jie Ren et al. in arxiv

A complete overview of the most essential components of data science and how to master them — If you are reading this article, it means that you are hoping to become a great data scientist and you just don’t know where to start. Although I am not an industry expert, I have been creating my own data science path for over 2 years now. I have been…

A comprehensive overview of the book, what I learned after reading it, and whether you should get it or not — Hands-on Machine Learning with Scikit-learn, Tensorflow & Keras is probably one of the most popular ML books (if not the most). I have just finished it recently and I enjoyed it so much that I thought it would be worth writing a book review about it. If you aren’t familiar…

Let’s dive into Parallel Reverse Attention Networks and explore their potential — As someone passionate about ML in healthcare, I was quite fascinated by PraNet [1]. I came across PraNet when I was doing Kaggle’s Kidney competition which was about identifying glomeruli (clusters of blood) in human kidney tissue images. …

A quick dive into the fundamentals of those 2 algorithms and when to use them — PCA & T-SNE are one of the most utilized dimensionality reduction algorithms. A wide problem in machine learning is the curse of dimensionality where typical machine learning algorithms underperform severely in high-dimensional spaces. …

Covering the theoretical aspects of K-means, Gaussian Mixture Models, and the completeness score — Unsupervised machine learning is teaching the machine learning algorithms to differentiate between data points without the knowledge of true labels. It is fairly more tricky than supervised learning, however more fun! Unsupervised learning comes with a few challenges such as evaluating the performance of the algorithms. In this article, we…

Let’s dive deep into the components of a web crawler — In part 1, we have established the fundamentals and requirements for designing a distributed web crawler. In this part, we are going to actually dive deep into the design. The design Seed URLs (Root URLs) Website URLs are essentially links to a server somewhere. The root URL is usually the URL with…