Google proposes efficient and modular Implicit Differentiation for Optimization Problems

A new Google Research study has proposed a unified, efficient and modular approach for implicit differentiation of optimization problems that combines the benefits of implicit differentiation and automatic differentiation (autodiff). The researchers say solvers equipped with implicit differentiation set up by the proposed framework can make the autodiff process more efficient for end-users.

Read More

Top 6 CI/ CD practices for End-to-End development pipelines

Continuous deployment

In this article, we’ll talk about some often-misunderstood development principles that will guide you to developing more resilient, production-ready development pipelines using CI/CD tools. Then, we’ll make it concrete with a tutorial about how to set up your own pipeline using Buddy.

Read More

Stratified splitting of grouped Datasets using optimization

One of the most frequent steps on a machine learning pipeline is splitting data into training and validation sets. It is one of the necessary skills all practitioners must master before tackling any problem. The splitting process requires a random shuffle of the data followed by a partition using a preset threshold. On classification variants, you may want to use stratification to ensure the same distribution of classes on both sets. When handling time series data, you might want to skip shuffling and keep the earliest observations on the training set.

Read More

How AI can learn from Genetics

Coding a solution for the 8-queens puzzle with Genetic Search Algorithms, AI algorithms that mimic how our genes are passed and expressed. James Watson and Francis Crick first published their groundbreaking study on the double-helix form of deoxyribonucleic acid (DNA) and how it expresses our genes, which up until then, were mere abstractions lacking a concrete, biological, definition.

Read More

The most Feature-Rich ML forecasting methods available: Compliments of RemixAutoML

This is my go-to method. The main difference between the CatBoost, XGBoost, and H2O versions relate to the ML parameters available for tuning. All functions listed in this blog have working examples in the GitHub README, the R help files (which can be opened in your R session) or the package reference manual.

Read More

How pandemic problem motivates AI developers to help Manufacturing Industries

The global pandemic has persuaded a number of manufacturers to pursue an AI-driven transformation of their operations, according to studies by Cap Gemini and the Boston Consulting Group. What has been noticed is the way in which they are combining human experience and insight with AI tools to find ways to differentiate themselves from their competitors.

Read More