Normalizing flows are one of the lesser known, yet fascinating and successful architectures in unsupervised deep learning. In this post we provide a basic introduction to flows using tfprobability, an R wrapper to TensorFlow Probability. Upcoming posts will build on this, using more complex flows on more complex data.
Use 3D to visualize matrix multiplication expressions, attention heads with real weights, and more.
Artificial Intelligence (AI) and Machine Learning (ML) have become transformative technologies across various industries. To keep up with the fast-paced advancements in the field, professionals and enthusiasts alike seek comprehensive training courses that provide in-depth knowledge and hands-on experience. In this article, we have curated a list of 100 training courses on AI and ML, covering various topics, skill levels, and application areas. Whether you are a beginner or an experienced practitioner, these courses will help you stay at the forefront of AI and ML developments.
Machine learning advancements lead to new ways to train models, as well as deceive them. This article discusses ways to train and defend against attacks.
We will cover often-overlooked concepts vital to NLP, such as Byte Pair Encoding, and discuss how understanding them leads to better models.
In this episode of Open Source Directions, we were joined by Thomas Wiecki once again who talked about the work being done with PyMC. PyMC3 is a Python package for Bayesian statistical modeling and Probabilistic Machine Learning focusing on advanced Markov chain Monte Carlo (MCMC) and variational inference (VI) algorithms. Its flexibility and extensibility make it applicable to a large suite of problems.
