Long Short-Term Memory (LSTM)

Machine learning models typically learn language by training on tasks like predicting the next word in a given text. Researchers trained a language model in a less focused, more human-like way.

During training, a neural network usually updates its weights according to an optimizer that’s tuned using hand-picked hyperparameters. New work eliminates the need for optimizer hyperparameters.

Sentence pairs that have equivalent meanings in different languages — typically used to train machine translation systems — have been available in sufficient quantities for only around 100 languages. New work doubled that number and produced a more capable model.

It’s surprisingly easy to turn a well-intended machine learning model to the dark side. In an experiment, Fabio Urbina and colleagues at Collaborations Pharmaceuticals, who had built a drug-discovery model to design useful compounds and avoid toxic ones, retrained it to generate poisons.

Nothing is certain except death and taxes, the saying goes — but how to make taxes fair and beneficial remains an open question. New research aims to answer it.

An Android app offers speech recognition model for speech impaired by cerebral palsy, Down syndrome, Parkinson’s disease, stroke, or traumatic brain injury.

Is human creativity being replaced by the synthetic equivalent? The fear: AI is cranking out increasingly sophisticated visual, musical, and literary works. AI-generated media will flood the market, squeezing out human artists and depriving the world of their creativity.

Neural networks translated a paralyzed man’s brainwaves into conversational phrases. Researchers trained a system to interpret electrical impulses from the brain of a man who had lost the ability to speak 15 years ago, and displayed them as words on a video screen.

Neural networks have learned to play video games like Dota 2 via reinforcement learning by playing for the equivalent of thousands of years (compressed into far less time). In new work, an automated player learned not by playing for millennia but by watching a few days’ worth of recorded gameplay.

An automated early warning system is alerting firefighters to emerging blazes.

Surgical robots perform millions of delicate operations annually under human control. Now they’re getting ready to operate on their own.

IBM’s Watson question-answering system stunned the world in 2011 when it bested human champions of the TV trivia game show Jeopardy! Although the Watson brand has fallen on hard times, the company’s language-processing prowess continues to develop.

An automated art critic spells out the emotional impact of images. Led by Panos Achlioptas, researchers at Ecole Polytechnique, King Abdullah University, and Stanford University trained a deep learning system to generate subjective interpretations of art.

Bayes-optimal algorithms always make the best decisions given their training and input, if certain assumptions hold true. New work shows that some neural networks can approach this kind of performance.

Neural nets could speed up development of new materials.What’s new: A deep learning system from Sandia National Laboratories dramatically accelerated simulations that help scientists understand how changes to the design or fabrication of a material change its properties.