Andrew Larimer

Cinematography for Robots: Building Quality Image Datasets for ML Training

Good ML models rely on good data. Machine Learning Practice Manager, Andrew Larimer will guide you through building a high-quality dataset for training vision models. We’ll consider: Camera and compute platform selection The balance between recording formats and network considerations How datasets can be built iteratively over time to lower the labeling burden guidelines for using …

Cinematography for Robots: Building Quality Image Datasets for ML Training Read More »

Cinematography-for-Robots-Building-Quality-Image-Datasets-for-ML-Training

Smart Government Series – Freeing Siloed Data: The Art of MOUs

Governments can uncover very useful insights when data is shared across agencies. But this can be a difficult task. Hint: The challenge isn’t the tech. In this episode, we unpack some common data-sharing challenges and remedies. We also share two inspiring examples of how data sharing has improved government services. Example 1: Virginia Vaccine Management and …

Smart Government Series – Freeing Siloed Data: The Art of MOUs Read More »

Smart Government Series – The Power of Machine Learning for Public Works Thumb

Smart Government Series – The Power of Machine Learning for Public Works

In this first episode of our Smart Government podcast series, we talk to Andrew Larimer, Practice Manager at SpringML. Andrew explains how some of the Vision AI use cases like pothole detection, combating urban blight, etc. help governments improve the quality of life for their citizens. He also addresses the challenges that may arise with the …

Smart Government Series – The Power of Machine Learning for Public Works Read More »

Smart Government Series – The Power of Machine Learning for Public Works Thumb

NBA Finals Game 6: Network Graph Analysis

One of the most useful ways to deploy Natural Language Processing at the moment is to uncover meaningful structure within unstructured text. While we’re nowhere near true machine comprehension of text, in this series of posts applying NLP to tweets about the NBA Finals, we’ve demonstrated a variety of techniques to extract meaningful data from text: sentiment analysis, topic clustering, numerical analysis of trends, time series analysis, etc. In this post, we want to look at another kind of structure we can often pull from text: the network graph represented by co-mentions of players & coaches.

NBA Game 6

NLP meets the NBA Finals Game 3: Topic Clustering

The Raptors are back on top after the NBA Finals Game 3, and just as with the last couple of games: we want to know what people are saying about it. We’ve looked at Twitter’s reactions to the last few games through the lens of sentiment analysis on its own, but today we’re adding a new tool from the Natural Language Processing (NLP) toolkit: topic clustering.

NBA Game 3

Warrior Sentiment Rebounds in Game 2 of the NBA Finals

In our last post, we saw that during Game 1 of the NBA Finals, the Raptors win saw more of a drop in sentiment for the Warriors than a spike in sentiment for the Raptors. With last nights’ Warriors win, we see some interesting trends that question that pattern.

NBA Game 2 Analysis

NBA Twitter Sentiment Analysis: Game 1

Following up on SpringML’s Game of Thrones Twitter Sentiment Analysis, we’ve decided to do a streaming sentiment analysis pipeline during the NBA Finals to monitor NBA fans reactions on Twitter. We set up the pipeline the same way as the Game of Thrones sentiment analysis.

NBA Twitter Sentiment Analysis

How Did Twitter React to Game of Thrones Finale?

Whether or not you’re a fan of the show, given a moderate amount of social media exposure over the past week, you probably noticed that Game of Thrones viewers’ emotions were running high as we headed into the show’s final episode. I was curious how fans would react to whatever ended up happening Sunday night, so I prepared a streaming sentiment analysis pipeline to keep a watch on Twitter to find out.

Game of Thrones