Before You Ask “Why”… Ask “Who”. Questions you’ll learn to ask when you… | by Cassie Kozyrkov | Sep, 2022

Questions you’ll learn to ask when you mature as a data scientist Here are the stages of evolution that you’ll go through if you’re lucky enough to have the opportunity to mature as a data scientist. Modified from a photo by Pawel Chu on Unsplash During the freshly hatched phase, the larval data scientist cheerfully

Artificial Intelligence is Transforming Modern Education | by Sanjay Adhikesaven | Sep, 2022

How AI impacts today’s classrooms and the exciting path forward From Martin Adams on Unsplash Authored by Sanjay Adhikesaven, Abyan Das, and Monish Muralicharan Artificial Intelligence (AI) has a pivotal role in many K-12 educational systems, providing benefits for both students and teachers. To best utilize AI’s potential, it is key for governments to implement

Critical Learning Periods in Deep Networks | by Cameron Wolfe | Sep, 2022

Why the first epochs matter the most… Empirical demonstration of the existence of critical learning periods in both artificial and biological system (from [1]) To understand critical learning periods within deep learning, it is helpful to first look at a related analogy to biological systems. Within humans and animals, critical periods are defined as times

Learning Semantics-Enriched Representation via Self-discovery, Self-Classification, and Self-Restoration: A Summary | by Anchit Bhattacharya | Sep, 2022

Get better results on scarce medical image datasets with a novel transfer learning technique to pretrain deep learning model Photo by Jonathan Borba on Unsplash One of the primary problems with applying machine learning and deep learning models to medical imaging tasks is the scarcity of sufficient data to train the model. Manual generation and

Classification of Neural Network Hyperparameters | by Rukshan Pramoditha | Sep, 2022

By network structure, learning and optimization, and regularization effect Photo by John-Mark Smith on Unsplash A major challenge when working with DL algorithms is setting and controlling hyperparameter values. This is technically called hyperparameter tuning or hyperparameter optimization. Hyperparameters control many aspects of DL algorithms. They can decide the time and computational cost of running

Google’s PaLM-SayCan: The First of the Next Generation of Robots | by Alberto Romero | Sep, 2022

Google has entered a new path: Merging AI and robotics. PaLM-SayCan picking up an apple. Credit: Google Research Despite what Google Search says, historically speaking, AI has had very little to do with shiny metallic robots with a human form. This doesn’t seem to be the case anymore. In the last couple of years, tech

4 Things to Know to Have a Better Understanding of Matplotlib | by Soner Yıldırım | Sep, 2022

Getting familiar with one of the original Python data visualization libraries Photo by Tolga Ulkan on Unsplash Matplotlib was one of the first tools I learned about in my data science journey. I was amazed by how it allows for customizing almost every little piece on a data visualization. On the other hand, its syntax

Hypothesis and Pandera: Generate Synthesis Pandas DataFrame for Testing | by Khuyen Tran | Sep, 2022

Create Clean and Robust Tests with Property-Based Testing Image by Author Imagine you are trying to figure out whether the function processing_fn is working properly. You use pytest to test the function with an example. The test passed, but you know that one example is not enough. You need to test the function with more