Post Thumb

Reading a neural network’s mind

A new analytic technique sheds light on inner workings of neural networks trained to perform natural-language-processing tasks, and even suggests possibilities for improving the performance of machine-translation systems.

Post Thumb

Will machines one day be as creative as humans? – Microsoft Research

Recent methods in artificial intelligence enable AI software to produce rich and creative digital artifacts such as text and images painted from scratch. One technique used in creating these artifacts are generative adversarial networks (GANs). Today at NIPS 2017, researchers from Microsoft Research and ETH Zurich present their work on making GAN models more robust …

Post Thumb

The Neural Network Zoo – The Asimov Institute

With new neural network architectures popping up every now and then, it’s hard to keep track of them all. Knowing all the abbreviations being thrown around (DCIGN, BiLSTM, DCGAN, anyone?) can be a bit overwhelming at first. So I decided to compose a cheat sheet containing many of those architectures. Most of these are neural networks, some are completely …

Post Thumb

Japan Pins Hopes on Floating Trains

Japan is set to start building a $90 billion magnetic-levitation rail system between Tokyo and Osaka, a technology that it hopes to turn into one of the country’s next big exports.