TensorFlow Lattice ensures your machine learning models follow global trends


Google's TensorFlow team released TensorFlow Lattice today to help developers ensure that their machine learning models adhere to global trends even when training data is noisy. A lookup table is a representation of data that includes inputs (keys) and outputs (values). Roughly speaking, the TensorFlow team's approach is to train the lookup table values using training data to maximize accuracy given constraints. This is really just a fancy way of saying that it allows developers to ensure that as inputs move in a single direction, outputs move in the same direction.