Top Twitter Topics by Data Scientists #21

Trending this week: How to perform continuous training in ML; 6 mistakes to avoid while training your ML model; Brain tumor detection using Mask R-CNN; Sharpen your DS skills.

Every week we analyze the most discussed topics on Twitter by Data Science & AI influencers.

The following topics, URLs, resources, and tweets have been automatically extracted using a topic modeling technique based on Sentence BERT, which we have enhanced to fit our use case.

Want to know more about the methodology used? Jump into this article for more details, and find the codes in this Github repository!


This week, Data Science and AI influencers on Twitter have talked about:

  • ML Dos and Don’ts
  • Deep Learning Use Cases
  • Sharpening Your Data Science Skills

The following sections provide all the details for each topic.

ML Dos and Don’ts

This week, influencers have shared some helpful advice and tips to apply to machine learning projects.

Amongst others, we have retained the following selection from KDnuggets who has shared:

A post that presents 6 Mistakes To Avoid While Training Your Machine Learning Model. This article provides some critical mistakes committed while training your model, that could make your model perform inaccurately and could also be disastrous while making crucial business decisions, especially in certain areas such as Healthcare or Self Driving Cars. In particular, this post focus on the 6 common mistakes you need to understand to make sure your AI model is successful.

An article that talks about the concept of continuous training in machine learning. Continuous training is a part of the MLOps practice which seeks to automatically and continuously retrain the model to adapt to changes that might occur in the data, and therefore to guarantee its good functioning in the production environment. This post details well the different strategies to be considered to perform continuous training properly depending on your specific business.

Then, a post titled “A Machine Learning Model Monitoring Checklist: 7 Things to Track”, which completes well the idea of continuous training by providing some keys to monitor your models in production and make sure that they keep performing at the expected levels as any disruption to model performance directly translates to the actual business loss. This article suggests how to monitor your models and provide open-source tools to use.

Deep Learning Uses Cases

The following paragraphs provide a selection of articles detailing some deep learning use cases in various domains.

KDnuggets has shared:

An article talking about Brain Tumor Detection using Mask R-CNN. Mask R-CNN is a deep learning model that represents the new state-of-the-art in terms of instance segmentation. This article shows how to build a Mask R-CNN model capable of detecting tumors from Magnetic Resonance Imaging (MRI) scans of the brain images. First, this post shares some simple understanding of Mask R-CNN and then shows you how to build your own model.

A post explaining how to perform Audio Data Analysis Using Deep Learning with Python. This article shows how to build a Convolutional Neural Network for music genre classification. More precisely, this post shows how a convolutional neural network (CNN) architecture is used for automatic feature extraction from audio data. It demonstrates that CNN is a viable alternative for such a task.

On his side, Kirk Borne has shared a post summarizing the problems in Cyber Security and the deep neural network algorithms that can address them. This article also provides a link to the paper A Survey of Deep Learning Methods for Cyber Security upon which it is based. This paper covers various deep learning algorithms in Cyber Security.

Sharpening Your Data Science Skills

This week, many AI influencers tweeted about the various resources to upskill your data science skills.

Ipfconline shared a list of the best programming languages to learn. The list includes the languages, how they stand out, and top companies which are using that language. They also shared a list of 11 data science skills for machine learning and AI. These skills are bucketed into different categories and explain the rationale behind including the skills in the list.

Dr. Ganapathi Pulipaka shared a list of more than 60 Data Science books. These books will help not only beginners but also advanced users to sharpen their data science skills.

Andreas Staub shared a 5 step Framework to plan AI projects effectively devised by Andres Ng. He and Terence Mills also shared an interesting article on 10 ML and AI project ideas for 2021. And finally, Bob E. Hayes shared an article that lists the 10 most in-demand AI jobs according to Indeed — and they all pay at least $95,000.