When Is There Not One Right Answer?

DiverseNet: When One Right Answer is not Enough

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple possible pixel values that could plausibly complete occluded image regions. State-of-the art supervised learning methods are typically optimized to make a s...

When the ICU is not the answer.

Metabolic surgery: who and when? Is there a good answer?

Currently there is little doubt that the body mass index ( BMI) is not an appropriate tool to grant access to metabolic surgery, especially in type 2 diabetics (T2D). Several studies are pointing towards other parameters that should go along with BMI in the treatment decision tree in non morbidly obese diabetics. Insulin resistance, fat distribution among others are considered good tools to pre...

Is there an answer?

Is There an Answer? is intended to serve as a forum in which readers to IUBMB Life may pose questions of the type that intrigue biochemists but for which there may be no obvious answer or one may be available but not widely known or easily accessible. Readers are invited to e-mail [email protected] if they have questions to contribute or if they can provide answers to questions that are provi...

When One Pipeline Is Not Enough

Pipelines that operate on buffers often work well to mitigate the high latency inherent in interprocessor communication and in accessing data on disk. Running a single pipeline on each node works well when each pipeline stage consumes and produces data at the same rate. If a stage might consume data faster or slower than it produces data, a single pipeline becomes unwieldy. We describe how we h...