Let’s see the sales in a Big Mart Store
Author(s): Saikat Biswas Originally published on Towards AI. Image by Anastasia Dulgier on Unsplash Predicting the sales of each product in a particular store We as Data Analysts and Data Science Practitioners are often challenged to predict the factors that have an …
Bad Data Equals Bad Predictive Model
Author(s): Benjamin Obi Tayo Ph.D. Originally published on Towards AI. Always question the source and quality of your data before using it for analysis or model building Image Source: Benjamin O. Tayo Data is key to any data science and machine learning …
Features in Image [Part -2]
Author(s): Akula Hemanth Kumar Originally published on Towards AI. Making computer vision easy with Monk, low code Deep Learning tool and a unified wrapper for Computer Vision. Feature extraction and visualization using OpenCV and PIL Level A features HoG features Histogram of …
The 4 P’s of Data Science Project Management
Author(s): Benjamin Obi Tayo Ph.D. Originally published on Towards AI. Plan, Prepare, Produce, and Publish your data science project Image Source: Pexels “By failing to prepare, you are preparing to fail” — Benjamin Franklin This article will discuss the 4 P’s of …
BatchNorm for Transfer Learning
Author(s): Michal Lukac Originally published on Towards AI. Making your networks to learn faster in TensorFlow 2+ source: Pexels There are still a lot of models that use Batch Normalization layers. If you would like to do transfer learning on such models, …
Various Ways to Get Data on Google Colab
Author(s): Sanchit Tanwar Originally published on Towards AI. Google colab is one of the best platforms for giving free GPU. It is one of the best places to experiment if you are starting with deep learning. One of the best things about …
Understanding BERT
Author(s): Shweta Baranwal Originally published on Towards AI. Source: Photo by Min An on Pexels Natural Language Processing BERT (Bidirectional Encoder Representations from Transformers) is a research paper published by Google AI language. Unlike previous versions of NLP architectures, BERT is conceptually …