Derivative of the Softmax Function and the Categorical Cross-Entropy Loss

In this short post, we are going to compute the Jacobian matrix of the softmax function. By applying an elegant computational trick, we will make the derivation super short. Using the obtained…

4 Way to Build Your Business Knowledge for Data Science Job

I am a true believer for any job position you have; you would always need to understand what your company is selling, AKA the business. You are hired within the company to improve the business…

You are underutilizing SHAP values: understanding populations and events

I have been working with SHAP values for some time, and have had the opportunity to test a lot of applications that I had never seen on the web, but which worked very nicely and so I wanted to share…

Fake Birds & Machine Learning

This article uses fictional data, previously generated using the code in an earlier article to illustrate the k-nearest neighbors classification algorithm. Readers can use this article as a cookbook…

How 2 Build a Cloud-Based ML Ops Framework in 2 weeks

How 2 Build a Cloud-Based ML Ops Framework in 2 weeks. In this post we will go through how we built a complete ML Ops framework in two weeks leaning on best practices of DevOps from software….

Ethereum Price Prediction 2021 Using Time Series Modeling

The year 2020 might have been the worst year for us however it was a golden year for cryptocurrency. 2020 has been the year of Bitcoin.2021 would be the start of the decade of Altcoins. The year saw…

AUTO ML — HyperOpt Sklearn

Now this method we will call it as HyperOpt for the popular Scikit-Learn machine learning library. An another extension of HyperOpt is HyperOpt-sklearn. It performs automatic search of data preparation methods, machine learning algorithms, and model hyperparameters for both classification and regression tasks

Apache Hadoop for Big Data

Big Data was the main reason for the emergence of Apache Hadoop. Humanity has never generated as much data as over the last 20 years at least. Because of this, we need new technologies, new software…

MLOPS-building a deep learning project from end to end (part-2)

In the previous part, we have completed building the pipelines and executing them using DVC. Now we will move toward the deployment part, before that we need a web app through which a user can…

Downtime is Money: Calculating the ROI on Data Quality

To quote a friend, “Building your data stack without factoring in data quality is like buying a Ferrari but keeping it in the garage.” In this article, guest columnist Francisco Alberini, Product…

towardsdatascience.com 13 hours ago