What’s creepier than images from the sci-fi TV series Doctor Who? Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who.

In training an image recognition model, it’s not uncommon to augment the data by cropping original images randomly. But if an image contains several objects, a cropped version may no longer match its label. Researchers developed a way to make sure random crops are labeled properly.

It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.

The University of Hong Kong, and Cornell University to create Neural Body, a procedure that generates novel views of a single human character based on shots from only a few angles.

The pandemic has pushed hospitals to their limits. A new machine learning system could help doctors make sure the most severe cases get timely, appropriate care.

The transformer architecture has inspired a plethora of variations. Yet researchers have used a patchwork of metrics to evaluate their performance, making them hard to compare. New work aims to level the playing field.

Models that interpret the interplay of words and images tend to be trained on richer bodies of text than images. Recent research worked toward giving such models a more balanced knowledge of the two domains.

Performance in language tasks rises with the size of the model — yet, as a model’s parameter count rises, so does the time it takes to render output. New work pumps up the number of parameters without slowing down the network.

Train a multilingual language translator to translate between Spanish and English and between English and German, and it may be able to translate directly between Spanish and German as well. New work proposes a simple path to better machine translation between languages.

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.

Doctors who treat breast cancer typically use a quick, inexpensive tumor-tissue stain test to diagnose the illness and a slower, more costly one to determine treatment. A new neural network could help doctors to go straight from diagnosis to treatment.

For children, associating a word with a picture that illustrates it helps them learn the word’s meaning. Research aims to do something similar for machine learning models. Researchers improved a BERT model’s performance on some language tasks by training it on a large dataset of image-word pairs.

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.

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.

Detecting earthquakes is an important step toward warning surrounding communities that damaging seismic waves may be headed their way. A new model detects tremors and provides clues to their epicenter.