Augmentation

Vision models can be improved by training them on several altered versions of the same image and also by encouraging their weights to be close to zero. Recent research showed that both can have adverse effects that may be difficult to detect.

Most U.S. state agencies use AI without limits or oversight. An investigative report probed reasons why efforts to rein them in have made little headway. Since 2018, nearly every proposed bill aimed at studying or controlling how state agencies use automated decision systems.

Synthetic datasets can inherit flaws in the real-world data they’re based on. Startups are working on solutions. Generating synthetic datasets for training machine learning systems is a booming business.

Trained on a small dataset, generative adversarial networks (GANs) tend to generate either replicas of the training data or noisy output. A new method spurs them to produce satisfying variations.

Convolutional neural networks are good at recognizing disease symptoms in medical scans of patients who were injected with iodine-based dye, that makes their organs more visible. But some patients can’t take the dye. Now synthetic scans from a GAN are helping CNNs learn to analyze undyed images.

In any training dataset, some classes may have relatively few examples. A new technique can improve a trained model’s performance on such underrepresented classes. Researchers introduced a method that synthesizes extracted features of underrepresented classes.

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.

The pandemic has forced self-driving car companies off the road. Now they’re moving forward by refining their mountains of training data. Self-driving cars typically collect real-world training data with two human operators onboard, but Covid-19 makes that unsafe at any speed.

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.

AI’s ability to produce synthetic pictures that fool humans into believing they’re real has spurred a race to build neural networks that can tell the difference. Recent research achieved encouraging results.

An unconventional approach to modifying data is cutting the amount of work required to train self-driving cars. Waymo unveiled a machine learning pipeline that varies lidar scans representing pedestrians and other objects.

When the world is panning for machine learning gold, it pays to help them dig through the data. Machine learning entrepreneurs can make their mark (and their fortune) building services that help other companies develop, deploy, and monitor AI, venture capitalist Rob Toews argues in Forbes.

In small data settings where labels are scarce, semi-supervised learning can train models by using a small number of labeled examples and a larger set of unlabeled examples. A new method outperforms earlier techniques.