- 10 Real-Life Applications of Reinforcement Learning, by Derrick Mwiti - Apr 12, 2021.
In this article, we’ll look at some of the real-world applications of reinforcement learning.
- Zero-Shot Learning: Can you classify an object without seeing it before?, by Nagesh Chauhan - Apr 12, 2021.
Developing machine learning models that can perform predictive functions on data it has never seen before has become an important research area called zero-shot learning. We tend to be pretty great at recognizing things in the world we never saw before, and zero-shot learning offers a possible path toward mimicking this powerful human capability.
- Top Stories, Apr 5-11: Awesome Tricks And Best Practices From Kaggle; How to deploy Machine Learning/Deep Learning models to the web - Apr 12, 2021.
Also: Shapash: Making Machine Learning Models Understandable; A/B Testing: 7 Common Questions and Answers in Data Science Interviews, Part 2; How to deploy Machine Learning/Deep Learning models to the web; Working With Time Series Using SQL
- How to Apply Transformers to Any Length of Text, by James Briggs - Apr 12, 2021.
Read on to find how to restore the power of NLP for long sequences.
- Interpretable Machine Learning: The Free eBook, by Matthew Mayo - Apr 9, 2021.
Interested in learning more about interpretability in machine learning? Check out this free eBook to learn about the basics, simple interpretable models, and strategies for interpreting more complex black box models.
- Deep Learning Recommendation Models (DLRM): A Deep Dive, by Nishant Kumar - Apr 9, 2021.
The currency in the 21st century is no longer just data. It's the attention of people. This deep dive article presents the architecture and deployment issues experienced with the deep learning recommendation model, DLRM, which was open-sourced by Facebook in March 2019.
- Deepfakes are now mainstream. What’s next?, by Dan Abdinoor - Apr 9, 2021.
Deepfakes have become mainstream. Here we take a closer look at recent news about deepfakes, and what it all might mean for the future.
- Can Robots and Humans Combat Extinction Together? Find Out April 17, by DataYap - Apr 8, 2021.
Get ready to trade that “Zoom fatigue” for Zoom euphoria at the DataYap Virtual Conference, Apr 17, where you’ll have your pick of 15 panels on some of the hottest topics in the data and technology space led by some of the top names in data science.
- NoSQL Explained: Understanding Key-Value Databases, by Alex Williams - Apr 8, 2021.
Among the four big NoSQL database types, key-value stores are probably the most popular ones due to their simplicity and fast performance. Let’s further explore how key-value stores work and what are their practical uses.
- Why machine learning struggles with causality, by Ben Dickson - Apr 8, 2021.
If there's one thing people know how to do, and that's guess what caused something else to happen. Usually these guesses are good, especially when making a visual observation of something in the physical world. AI continues to wrestle with such inference of causality, and fundamental challenges must be overcome before we can have "intuitive" machine learning.
- A/B Testing: 7 Common Questions and Answers in Data Science Interviews, Part 2, by Emma Ding - Apr 8, 2021.
In this second article in this series, we’ll continue to take an interview-driven approach by linking some of the most commonly asked interview questions to different components of A/B testing, including selecting ideas for testing, designing A/B tests, evaluating test results, and making ship or no ship decisions.
- Start a Career in a Growing Field with Google’s Data Analytics Professional Certificate, by Coursera - Apr 7, 2021.
Google's recently launched Data Analytics Professional Certificate on Coursera is great for anyone, regardless of background or experience. The program is completely online, self-paced, and costs $39 per month. Interested in preparing for a new career in a high-growth field?
- E-commerce Data Analysis for Sales Strategy Using Python, by Juhi Sharma - Apr 7, 2021.
Check out this informative and concise case study applying data analysis using Python to a well-defined e-commerce scenario.
- How to Make Sure Your Analysis Actually Gets Used, by Taylor Count - Apr 7, 2021.
Few things are as demoralizing as seeing your data analysis tossed aside. Learn from these tips -- assembled from experience, academic research, and industry best practice -- on how to make sure your hard work receives the credit it deserves and delivers the value to your organization that you expect.
- Microsoft Research Trains Neural Networks to Understand What They Read, by Jesus Rodriguez - Apr 7, 2021.
The new models make inroads in a new areas of deep learning known as machine reading comprehension.
- Working With Time Series Using SQL, by Michael Grogan - Apr 6, 2021.
This article is an overview of using SQL to manipulate time series data.
- How Noisy Labels Impact Machine Learning Models, by iMerit - Apr 6, 2021.
Not all training data labeling errors have the same impact on the performance of the Machine Learning system. The structure of the labeling errors make a difference. Read iMerit’s latest blog to learn how to minimize the impact of labeling errors.
- KDnuggets Top Blogs Reward Program, by Gregory Piatetsky - Apr 6, 2021.
To encourage more high-quality and especially original contributions to KDnuggets, we announce KDnuggets Top Blogs Reward program, where we will pay the authors of top blogs published each month, starting with blogs submitted April 7 or later.
- How to Dockerize Any Machine Learning Application, by Arunn Thevapalan - Apr 6, 2021.
How can you -- an awesome Data Scientist -- also be known as an awesome software engineer? Docker. And these 3 simple steps to use it for your solutions over and over again.
- Automated Text Classification with EvalML, by Angela Lin - Apr 6, 2021.
Learn how EvalML leverages Woodwork, Featuretools and the nlp-primitives library to process text data and create a machine learning model that can detect spam text messages.
- Top Stories, Mar 29 – Apr 4: Top 10 Python Libraries Data Scientists should know in 2021; Shapash: Making Machine Learning Models Understandable - Apr 5, 2021.
Also: The 8 Most Common Data Scientists; Easy AutoML in Python; How to Succeed in Becoming a Freelance Data Scientist; The 8 Most Common Data Scientists
- The Best Machine Learning Frameworks & Extensions for TensorFlow, by Derrick Mwiti - Apr 5, 2021.
Check out this curated list of useful frameworks and extensions for TensorFlow.
- How to deploy Machine Learning/Deep Learning models to the web, by Ahmad Anis - Apr 5, 2021.
The full value of your deep learning models comes from enabling others to use them. Learn how to deploy your model to the web and access it as a REST API, and begin to share the power of your machine learning development with the world.
- Awesome Tricks And Best Practices From Kaggle, by Bex T. - Apr 5, 2021.
Easily learn what is only learned by hours of search and exploration.
- One Million KDnuggets Visitors in March. Wow., by Gregory Piatetsky - Apr 3, 2021.
KDnuggets has reached an amazing milestone of one million unique visitors in March 2021. We review how we got here.
- What did COVID do to all our models?, by Heather Fyson - Apr 2, 2021.
An interview with Dean Abbott and John Elder about change management, complexity, interpretability, and the risk of AI taking over humanity.
- Shapash: Making Machine Learning Models Understandable, by Yann Golhen - Apr 2, 2021.
Establishing an expectation for trust around AI technologies may soon become one of the most important skills provided by Data Scientists. Significant research investments are underway in this area, and new tools are being developed, such as Shapash, an open-source Python library that helps Data Scientists make machine learning models more transparent and understandable.
- What’s ETL?, by Omer Mahmood - Apr 2, 2021.
Discover what ETL is, and see in what ways it’s critical for data science.
- Easy AutoML in Python, by Dylan Sherry - Apr 1, 2021.
We’re excited to announce that a new open-source project has joined the Alteryx open-source ecosystem. EvalML is a library for automated machine learning (AutoML) and model understanding, written in Python.
- The 8 Most Common Data Scientists, by JABDE - Apr 1, 2021.
Admit it all you wanna-be, newbie, and old-old-school Data Scientists on the planet, whether you like it or not, you've probably behaved like one of these types. Or two. Or all eight.
- A/B Testing: 7 Common Questions and Answers in Data Science Interviews, Part 1, by Emma Ding - Apr 1, 2021.
In this article, we’ll take an interview-driven approach by linking some of the most commonly asked interview questions to different components of A/B testing, including selecting ideas for testing, designing A/B tests, evaluating test results, and making ship or no ship decisions.