Machine Learning

Design patterns are not just a way to structure code. They also communicate the problem addressed and how the code or component is intended to be used. Link

Since their introduction in 2017, transformers have revolutionized Natural Language Processing (NLP). Now, transformers are finding applications all over Deep Learning, be it computer vision (CV), reinforcement learning (RL), Generative Adversarial Networks (GANs), Speech or even Biology. Among other things, transformers have enabled the creation of powerful language models like GPT-3 and were instrumental in DeepMind’s recent AlphaFold2, that tackles protein folding. Link

One of the trickiest interview rounds for ML practitioners is ML systems design. If you’re applying to be a Data Scientist, ML Engineer or ML Manager at a big tech company, you’ll probably face an ML Systems design question. I recently tackled this question at a few big tech companies on my way to becoming a Staff ML Engineer at Pinterest. In this article I’m going to talk about how to approach ML Systems Design interviews, core concepts to know and I’ll provide links to some of the resources I used.

For data scientists and data engineers, d6tflow is a python library which makes building complex data science workflows easy, fast and intuitive. It is primarily designed for data scientists to build better models faster. For data engineers, it can also be a lightweight alternative and help productionize data science models faster. Unlike other data pipeline/workflow solutions, d6tflow focuses on managing data science research workflows instead of managing production data pipelines.

A step-by-step guide with code examples Link [Link] (https://habr.com/ru/company/vk/blog/673914/)

Machine learning operations (MLOps) is becoming an exciting space as we figure out the best practices and technologies to deploy machine learning models in the real world. MLOps enable ML teams to build responsible and scalable machine learning systems and infrastructure. Link

A time series is a sequence of data points indexed in time order. It’s an observation of the same variable at successive points in time. In other words, it’s a set of data that has been observed over a period of time. Link

To start with, we present an overall system diagram for recommendation systems in the following figure. The main components of the architecture contain one or more machine learning algorithms. Link Link

This article will help you strengthen your plan by providing you with a learning framework, resources, and project ideas to aid in the development of a robust portfolio of work demonstrating data science ability. Link

A Time-Series is a sequence of data points collected at different timestamps. These are essentially successive measurements collected from the same data source at the same time interval. Further, we can use these chronologically gathered readings to monitor trends and changes over time. The time-series models can be univariate or multivariate. The univariate time series models are implemented when the dependent variable is a single time series, like room temperature measurement from a single sensor.

Machine Learning sample apps - this repo provides sample code to support my articles on Towards Data Science and Youtube channel. Link

The T5 Transformer frames any NLP task as a text-to-text task enabling pre-trained models to easily learn new tasks. Let’s teach the old dog a new trick! Link

An easy-to-follow comprehensive guide on using a stack of powerful tools to train and serve an AutoML pipeline for insurance cross-sell Link

We will start by discussing what recommender systems are and what are their applications and benefits. We will also compare the main techniques of building machine learning models for recommender systems and take a look at metrics and business evaluation techniques. Finally, we are going to see how to choose these metrics for the required evaluation.

The challenge of establishing reference architectures for large-scale machine learning solutions is accentuated by two main factors: Machine learning frameworks and infrastructure have evolved considerably faster than the adoption of those technologies in mainstream environments. The lifecycle of machine learning solutions is fundamentally different from other software disciplines. Link