We decided to approach this problem as a similarity learning modeling effort. We used convolutional neural networks to train a model that takes an image or video as input and outputs a vector representation of the input, such that similar inputs will be close to each other in the vector space. The vector learning is driven by a triplet loss function.
Object detection in video has become a matter of routine, however, expanding these models to detect an object of your choosing requires many thousands, if not tens of thousands, of training examples. Few shot learners seek to make this process cheaper and easier by learning to detect new objects with only a small handful of examples (i.e. 1-30).
Deep learning, specifically computer vision and natural language processing, can be designed to identify defects during the product packaging process. These deep learning models can verify that a label on a package is present, correct, straight, and readable.
Mosaic designed and deployed custom computer vision models to automate asset recognition & inform inspection decisions.
Traditional lending practices are a prime candidate for machine learning improvements. Lenders can make more accurate and faster decisions by shifting decision-making from analysis of individuals to analysis of trends and patterns.
Natural language models have come a long way in the past couple of years. With the advent of the deep learning Transformer architecture, it became possible to generate text that could, plausibly, be passed off as written by a human.
Mosaic built an automated cooking prediction & optimizer using deep reinforcement learning to improve short term cooking operations.
Weather has a high impact on operations in many industries, and therefore is of great value to integrate into strategic decision making. Mosaic has roots in aviation research & development, giving us deep expertise in combining weather data streams with planning applications to facilitate efficient resource allocation.