Use this methodology (1) to find the best solution instead of executing the first idea that crosses your mind; (2) to minimize (and enable) the delivery time of complex research projects in data science.
topbots.com/complex-research…#AI#MachineLearning#Research#ML
We all love big language models, but there are some dark sides we should be aware of. Here's an overview showing that language models like BERT and GPT-2 can generate hurtful statements – not only in English but across different languages.
topbots.com/can-too-much-ber…#BERT#NLP#ML
When we do online experiments or A/B testing, we need to ensure our test has high statistical power so that we can find the experimental effect if it does exist. In this article, will walk you through several popular variance reduction methods.
topbots.com/online-experimen…#AI
Can we make GANs using Vision Transformers? In this article, Davide Coccomini investigates the creative side of Vision Transformers with two different model architectures: TransGAN and Paint Transformer.
topbots.com/the-creative-sid…#ML#MachineLearning#ComputerVIsion#AI
What if you need to analyze an SQL database consisting of 500 tables? Check this article to see how to build a tool in which you can apply various filters and then view the filtered tables in an easy-to-grasp visual representation.
topbots.com/visualize-databa…#ML#AI#Python
When combining multiple models into a group model, you get an ensemble model that usually performs better than each model alone. Check this article for Python implementations of such popular ensemble methods as voting, bagging, boosting, and stacking.
topbots.com/practical-guide-…
Survival analysis can be applied in medicine as patients’ survival time analysis, in engineering as reliability analysis or time-to-failure analysis, and in economics as duration analysis. Read this practical guide by Idil Izmiguzel.
topbots.com/survival-analysi…#ML#Python#AI
The question we ask the A/B test is “which version is better?”. Except for the traditional Frequentist framework, Bayesian framework can also answer this question and is gaining more and more popularity in the online industries.
topbots.com/switch-to-bayesi…#ML#Bayesian#ABtesting
Varshita Sher shares a few tips for writing cleaner code in Python. Including these tips as part of your everyday coding routine will help you generate supreme quality Python scripts, that are easily maintainable and scalable over time.
topbots.com/data-scientists-…#AI#Python
Follow this tutorial by Varshita Sher to build a facial identification system that will verify if an image, generally known as a probe image, exists within a pre-existing database of faces, generally known as the evaluation set.
topbots.com/building-face-re…#AI#FaceRecognition#ML
Over the centuries, we have seen how the universe was discovered by scientists and imagined by artists, but what would an artificial intelligence think? How would it imagine the universe? We are now able to answer these questions, thanks to GANs.
topbots.com/how-does-an-ai-i…#GAN#ML
Vision Transformers can achieve better results than other methods. Davide Coccomini shows that realising self-supervised approaches for Vision Transformers may be a possible way to making these models not only powerful but also easier to apply.
topbots.com/self-supervised-…#ML#AI
Are you interested to know how AI is applied to count penguins from space? Or prevent substance abuse, predict pandemics, analyze people's mental health? Matthew Stewart introduces the reader to the nascent research field of AI for Social Good.
topbots.com/introduction-to-…#AI4SG#AI
In this tutorial, Florent Poux features some of the top and robust approaches to 3D point cloud segmentation:
✅ RANSAC or RANdom SAmple Consensus
✅ Euclidean Clustering through DBSCAN or Density-Based Spatial Clustering of Applications w/ Noise
topbots.com/automate-3d-poin…#ML#AI
Here Ane Berasategi shares her tips on following the latest advances in deep learning by reading research papers.
It is not so easy to shortlist the top papers. Read the article for some good resources.
topbots.com/learn-deep-learn…#ML#AI#DeepLearning#MachineLearning
Isn’t there a way to get the best out of both Convolutional Neural Networks and Vision Transformers? Davide Coccomini shows how these two architectures can be combined to obtain something capable of exploiting the positive sides of both!
topbots.com/vision-transform…#AI#Transformers
Transformer-based language models show impressive performance in text generation but controlling their output remains challenging. Rohola Zandie addresses the problem of controlled text generation without the massive infrastructure to train it!
topbots.com/topical-language…#AI#ML
Duncan and his teammates describe their Convolutional Neural Network model to recognize and classify different types of waste items! If you’ve ever wondered how AI can help us recycle, this is it.
topbots.com/how-ai-can-help-…#MachineLearning#AI#ML#CNN#recycle