Machine Learning

VC Astasia Myers’ perspectives on machine learning, cloud infrastructure, developer tools, open source, and security. Sign up here. There are two approaches to building Machine Learning (ML) applications. Traditionally, data scientists and ML engineers trained or fine-tuned ML models they deployed to production as a notebook or API. Recently a…

Demonstrating the power of neuro-symbolic programming — In the last few years, we have seen a rise of Transformer¹ based models with successful applications in many fields, such as Natural Language Processing or Computer Vision. In this article, we will explore a concise, explainable, and extendable way to express deep learning models, specifically transformers, as a hybrid…

A modification of this popular algorithm that builds clusters balanced in the number of points — Clustering is a methodology used to group data points containing similar features among them. …

Advice and techniques to ensure success — The conversion of a model checkpoint from one framework to another could be a complex process if you want to maintain the same level of performance. In the past, I was asked to evaluate my work on the MLPerf inference benchmark suite. MLPerf is an industry benchmark for measuring the…

Overview of a cloud-native computer-aided drug discovery solution built with Kubernetes. — Computer-aided drug design (CADD), also known as in silico screening, has become an effective technique in cutting down the time and money it takes to discover new drugs. As the name implies, this process involves using computing resources, and the increased adoption of advanced Machine Learning (ML) models operating on…

Deconstructing and Understanding this Beautiful Algorithm — In classical Machine Learning, Random Forests have been a silver bullet type of model. The model is great for a few reasons: Requires less preprocessing of data compared to many other algorithms, which makes it easy to set up Acts as either a classification or regression model Less prone to…