It's something we all do, yet is often seen as a taboo subject. Now, scientists are finally lifting the lid on our bowel movements, with the launch of a new camera for your toilet. Researchers from Throne Science have developed a bizarre device that clips onto the side of the bowl, and uses AI to analyse your stools. Thankfully, you won't be shown the photos themselves, and instead will receive a breakdown on the shape, size and structure of your waste. 'Monitoring bowel movements can provide valuable insights into digestive health and nutrient absorption, as well as serve as an early warning sign for various conditions like gastrointestinal bleeding,' Throne Science explains on its website.

In much of machine learning, data used for training and inference undergoes a preprocessing step, where multiple inputs (such as images) are scaled to the same dimensions and stacked into batches. This lets high-performance deep learning libraries like TensorFlow run the same computation graph across all the inputs in the batch in parallel. Batching exploits the SIMD capabilities of modern GPUs and multi-core CPUs to speed up execution. However, there are many problem domains where the size and structure of the input data varies, such as parse trees in natural language understanding, abstract syntax trees in source code, DOM trees for web pages and more. In these cases, the different inputs have different computation graphs that don't naturally batch together, resulting in poor processor, memory, and cache utilization. Today we are releasing TensorFlow Fold to address these challenges.