Intro

Through the telecommunication boom, Claude Shannon, in his seminal 1948 paper¹, posed a matter that may revolutionise technology:How can we quantify communication?Shannon’s findings remain fundamental to expressing information quantification, storage, and communication. These insights...

Sign up here to receive it at no cost. Or for those who’re already an AI aficionado, send it on to someone in your life who’s inquisitive about the technology but is just beginning...

An introduction to the mechanics of AutoDiff, exploring its mathematical principles, implementation strategies, and applications in currently most-used frameworksAt the center of machine learning lies the optimization of loss/objective functions. This optimization process heavily...

For simplicity we’ll examine Simpson’s paradox specializing in two cohorts, female and male adults.I’ll be the primary to confess that I struggled to grasp this idea and it took me three weekends of deep...

What about default values and argument extractions?from pydantic import validate_call@validate_call(validate_return=True)def add(*args: int, a: int, b: int = 4) -> int:return str(sum(args) + a + b)# ----add(4,3,4)> ValidationError: 1 validation error for addaMissing required keyword...

A programmatic approach to make use of models behind ChatGPT.ChatGPT needs no further introduction lately and on this post we would love to look deeper into how we will programmatically interact with the models...

2.1. Support Vector Machines and Iris Data SetIn a previous post I used Grid Search, Random Search and Bayesian Optimization for hyperparameter optimization using the Iris data set provided by scikit-learn. Iris data set...

Graph Neural Networks (GNNs) are one in every of the fastest-growing tools in machine learning. GNNs mix a wealthy array of feature data (much like the input of a standard neural network) with network...