What is A/B Testing?Almost everyone hated learning statistics (well, maybe except some statisticians). With all those distributions and critical values that we needed to memorize, we just ended up with a headache. You might have swore not to ever touch the subject again; that is, until you had to analyze an A/B test.A/B testing is the “fun” name … [Read more...] about Why You Should Switch To Bayesian A/B Testing
Data Science & Engineering
Introduction To AI For Social Good
AI for Social Good — a relatively new research field at the intersection of AI and a number of other fields. Source“Whenever I hear people saying AI is going to hurt people in the future I think, yeah, technology can generally always be used for good and bad and you need to be careful about how you build it … if you’re arguing against AI then you’re arguing against … [Read more...] about Introduction To AI For Social Good
Should Machine Learning Experts Respond to Climate Change Call To Action?
Our planet's proper functioning and survival rely on a delicate balance of a vast heterogeneity of animal, plant, and microorganism species that contribute to the ecosystem established on Earth.Of all the organisms, there is one that has had a great impact on the planet, so great that it was capable of upsetting its balance, causing entire ecosystems to disappear and … [Read more...] about Should Machine Learning Experts Respond to Climate Change Call To Action?
Is Attention What You Really Need In Transformers?
In recent years there has been an explosion of methods based on self-attention and in particular Transformers, first in the field of Natural Language Processing and recently also in the field of Computer Vision.If you don’t know what Transformers are, or if you want to know more about the mechanism of self-attention, I suggest you have a look at my first article on this … [Read more...] about Is Attention What You Really Need In Transformers?
Advanced Forecasting Using Bayesian Diffusion Modeling
Across all areas of data science there is huge demand for innovative modeling solutions aimed at forecasting and elucidating dynamic phenomena. High profile use cases of modeling and forecasting dynamic phenomena include:Finance — prediction of share price movements or commodity price fluctuationsBiomedical science — prediction of biological trajectories, e.g. … [Read more...] about Advanced Forecasting Using Bayesian Diffusion Modeling
What Is Your Model Hiding? A Tutorial on Evaluating ML Models
Imagine you trained a machine learning model. Maybe, a couple of candidates to choose from.You ran them on the test set and got some quality estimates. Models are not overfitted. Features make sense. Overall, they perform as well as they can, given the limited data at hand.Now, it is time to decide if any of them is good enough for production use. How to evaluate … [Read more...] about What Is Your Model Hiding? A Tutorial on Evaluating ML Models
A Comprehensive Introduction to Bayesian Deep Learning
Photo by Cody Hiscox on UnsplashPreamble Neural Network Generalization Back to Basics: The Bayesian Approach Frequentists Bayesianists Bayesian Inference and Marginalization How to Use a Posterior in Practice? Maximum A Posteriori Estimation Full Predictive Distribution Approximate Predictive Distribution Bayesian Deep Learning Recent Approaches to Bayesian Deep … [Read more...] about A Comprehensive Introduction to Bayesian Deep Learning
Graph Transformer: A Generalization of Transformers to Graphs
This blog is based on the paper A Generalization of Transformer Networks to Graphs with Xavier Bresson at 2021 AAAI Workshop on Deep Learning on Graphs: Methods and Applications (DLG-AAAI’21).We present Graph Transformer, a transformer neural network that can operate on arbitrary graphs.BLOG OUTLINE:BackgroundObjectiveKey Design Aspects for … [Read more...] about Graph Transformer: A Generalization of Transformers to Graphs
Autoencoders: Overview of Research and Applications
Since the early days of machine learning, it has been attempted to learn good representations of data in an unsupervised manner. The hypothesis underlying this effort is that disentangled representations translate well to downstream supervised tasks. For example, if a human is told that a Tesla is a car and he has a good representation of what a car looks like, he can probably … [Read more...] about Autoencoders: Overview of Research and Applications
Variational Methods in Deep Learning
Deep neural networks are a flexible family of models wide applications in AI and other fields. Even though these networks often encompass millions or even billions of parameters, it is still possible to train them effectively using the maximum likelihood principle as well as stochastic gradient descent techniques. Unfortunately, this learning procedure only gives us a … [Read more...] about Variational Methods in Deep Learning