NSL works with with the TensorFlow machine learning platform and is made to work for both experienced and inexperienced machine learning practitioners. NSL can make models for computer vision, perform NLP, and run predictions from graphical datasets like medical records or knowledge graphs.
“Leveraging structured signals during training allows developers to achieve higher model accuracy, particularly when the amount of labeled data is relatively small,” TensorFlow engineers said in a blog post today. “Training with structured signals also leads to more robust models. These techniques have been widely used in Google for improving model performance, such as learning image semantic embedding.”
NSL can train with supervised, semi-supervised, or unsupervised learning to create models that use graphical signals for regularization during training, in some instances with less than five lines of code.
The new framework also includes tools to help developers structure data and APIs for the creation of adversarial training examples with little code.
In other AI news, last week Google AI, previously known as Google Research, open-sourced SM3, an optimizer for large-scale language understanding models like Google’s BERT and OpenAI’s GPT2.
The audio problem: Learn how new cloud-based API solutions are solving imperfect, frustrating audio in video conferences. Access here