• Similarity Learning for Image Geolocation

    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.

    Read More

  • Few Shot Learning for Computer Vision

    Few Shot Learning for Computer Vision

    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).

    Read More

  • MLOps tools, tips, & tricks: MLflow Model Registry

    MLOps tools, tips, & tricks: MLflow Model Registry

    MLflow is open-source software initially developed by DataBricks for managing the “machine learning lifecycle.” It makes the model artifacts and their environment specifications more readily available when assembling ML model applications or for other purposes such as collaborating with teammates

    Read More

  • Transformer and Computer-generated Document Summaries

    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.

    Read More

  • Skynet progress update: GPT-3

    To understand GPT-3, it’s helpful to understand a little bit about the history of language models. The language of computers is numbers. The input to all machine learning algorithms is ultimately numbers as well.

    Read More

  • Managing Business Travel Risk with Machine Learning

    Mosaic is developing a machine learning based tool that assists corporate travel manages and business travelers in making the safest travel decisions possible.

    Read More

  • Algorithm Quality Assurance via Auditing & MLops

    Algorithm Quality Assurance via Auditing & MLops

    Algorithms can be trained to mimic human behavior, but what happens when the human developing the algorithm inadvertently allows bias into the training process?

    Read More

  • Moving Fast & Deploying Predictive Analytics

    Moving Fast & Deploying Predictive Analytics

    Working in conjunction with subject matter experts, data scientists can swiftly apply statistical tools and uncover emerging trends. This is extremely valuable for companies trying to operate in a disruption. Not only will executives have an accurate representation of their present situation, but new products & services can be devised from these insights.

    Read More

  • Combat Supply Chain Disruptions with Data Science

    Combat Supply Chain Disruptions with Data Science

    Global external shocks are going to continue to happen, that is a fact of operating a business in today’s environment. As companies embrace data science in their decision-making processes, they are better positioned to deal with these disruptions, allowing them to manage a risk-optimized supply chain.

    Read More

  • What is Computer Vision & why you should be implementing it

    What is Computer Vision & why you should be implementing it

    Designing and deploying computer vision is a powerful technology that humans can employ to improve their decision making. The only limits to these technologies lie within our ability to think of problems for them to solve.

    Read More