Zero-knowledge p2p cloud storage

AI is synonymous with surveillance. Is it? At Cubbit, we do things differently. Cubbit is a zero-knowledge p2p cloud storage platform: no server stores your files and no one can access them without your permission - not even us. Our AI coordinator is cryptographically blind, meaning that it never gets access to your files or their encryption keys, which are stored client-side. Learn more!

The Bayesian Learning Rule

We show that many machine-learning algorithms are specific instances of a single algorithm called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide-range of algorithms from fields such as optimization, deep learning, and graphical models. This includes classical algorithms such as ridge regression, Newton's method, and Kalman filter, as well as modern deep-learning algorithms such as stochastic-gradient descent, RMSprop, and Dropout. The key idea in deriving such algorithms is to approximate the posterior using candidate distributions estimated by using natural gradients. Different candidate distributions result in different algorithms and further approximations to natural gradients give rise to variants of those algorithms. Our work not only unifies, generalizes, and improves existing algorithms, but also helps us design new ones.

QA-GNN model that reasons with language models and knowledge graphs

Question-answering systems are the backbone of our digital lives. From search engines to personal assistants, we use them every day and never even realize it! For example, when you ask a question like “Where was Leonardo da Vinci born?” these intelligent computer programs need to gather background knowledge about him (Leonardo’s birthplace is Italy) as well as computational reasoning over that information in order for an answer to be generated – which will often happen automatically without us even realizing what happened behind the scenes.

RMA: Rapid motor adaptation for legged robot

Successful real-world deployment of legged robots would require them to adapt in real-time to unseen scenarios like changing terrains, changing payloads, wear and tear. This paper presents Rapid Motor Adaptation (RMA) algorithm to solve this problem of real-time online adaptation in quadruped robots.

Predict which Scooby Doo monsters 👻 are REAL with a tuned decision tree model

This is the latest in my series of screencasts demonstrating how to use the tidymodels packages, from just getting started to tuning more complex models. Today’s screencast walks through how to train and evalute a random forest model, with this week’s #TidyTuesday dataset on Scooby Doo episodes. 👻

Complete glossary of Keras Neural Network layers

Learn the purpose and instantiation for Core layers, Pooling layers, Preprocessing layers, etc.