In this recording we share how SpringML leverages Machine Learning to create social distancing compliance solutions leveraging Google Cloud Vision AI. Our frameworks allow for rapid detection from any video feed when people are not wearing personal protective equipment (PPE) or complying with social distancing guidelines.
Automating Clinical Workflows with Google’s Healthcare API Read More »
Due to COVID-19 all sorts of organizations are experiencing floods of applications. SpringML can quickly and cost effectively build an applicant intake solution on Google Cloud helping to manage application surges.
Dialogue avec notre VP Science des Donnee sur AI Vision et Cloud Auto ML pour Michelin.
With the urgent need to better understand the spread of COVID-19 many mobile device companies are making location data available. We applaud Google and Apple for not only making this data available to everybody in an easy comma-delimited file but also to ensure it’s anonymized.
In this blog we walk-through how to train an autoencoder model using a dataset of customers with good financial profiles that are seeking loans. The autoencoder will learn the common traits that make a customer a “good” credit risk.
In this blog we will explore how deep learning techniques developed for image analysis and classification can be leveraged to detect if lungs have been infected due to coronavirus.
In this report, we compare two technologies that have come out of Google for managing machine learning Pipelines. The first is Kubeflow, which has been in development since 2018 and was originated as a way of bringing the ideas of TFX (used only internally at Google at the time) to the public via open source tools and is in the process of changing as many developments as open source tools come and go. The second is TensorFlow Extended (TFX) itself. Google announced that it would be making TFX available to the public at the end of 2018.
Modeling is about understanding behavior. It’s mostly applied towards commercial goals, but it will warm your heart and fill it with purpose when you apply it towards helping real people and especially our youth. Applied data science requires good data and good modeling skills but also a lot of pre- and post- analysis and workflow planning. This can go a long way in not only identifying who is at risk but tailoring the best intervention to help, in our case students, get back on track. And that’s the big picture.
