Blogs Archives | Page 2 of 7 | Mosaic Data Science

Blogs

A Guide to Addressing Culture in Digital Transformation

In this blog post, Mosaic examines how to identify & measure culture during a digital transformation.

By Sel Gerosa, 3 yearsSeptember 9, 2021 ago

Blogs

Deriving value from IoT and sensor data with time series classification (TSC)

Anytime you wish to predict the transient state(s) of something or someone constantly monitored by sensors, time series classifications are the right tool. This article will explain some basic concepts of using deep learning models for TSC and finish with a brief discussion of ways to improve the performance to save on cost and speed.

By Sel Gerosa, 3 yearsJuly 28, 2021 ago

Blogs

Transformation: AI

Mosaic sees Digital Transformation differently; our view is that while the technology is a critical part of any Digital Transformation, it’s only a part of a greater whole that includes people, process, and culture change that all combine to enable effective use of the technology.

By Sel Gerosa, 3 yearsMay 24, 2021 ago

Blogs

A Review of Open-Source Annotation Tools for Computer Vision

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.

By Drew Clancy, 3 yearsFebruary 17, 2021 ago

Blogs

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.

By Drew Clancy, 3 yearsJanuary 19, 2021 ago

Blogs

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).

By Drew Clancy, 3 yearsDecember 8, 2020 ago

Blogs

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

By Drew Clancy, 4 yearsOctober 16, 2020 ago

Blogs

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.

By Drew Clancy, 4 yearsAugust 25, 2020 ago

Blogs

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.

By Drew Clancy, 4 yearsAugust 25, 2020 ago

Blogs

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.

By Drew Clancy, 4 yearsJuly 15, 2020 ago