Case Study

Reinforcement Learning for Power Generation

Thu Apr 20, 2023, by Winder.AI, in Case Study, Reinforcement Learning

Genesis Energy is a power generation company in New Zealand that sells electricity generated by hydroelectric and hydrothermal generators to the domestic energy market. Currently, people control the decisions surrounding power generation and pricing. Genesis asked Winder.AI to help them develop a reinforcement learning-powered solution to automate generation and pricing. Reinforcement Learning Problem New Zealand has the enviable situation of possessing high-altitude lakes refilled with ice melt. Discharging the lake presents an ample kinetic energy store that can be utilised for power generation via a turbine.

Presentation: MLOps and the Online Safety Bill

Tue Mar 21, 2023, by Phil Winder, in MLOps, Case Study, Talk

This is a video of a presentation about the UK’s online safety bill. This places new burdens on social media companies to moderate content to keep the public safe. This video discusses how platforms are using MLOps to help operate AI solutions that allow them to scale and prevent hundreds of violating posts from being published every second.

How Social Media Platforms use MLOps and AI Governance to Help to Moderate Content

Mon Jan 30, 2023, by Winder.AI, in MLOps, Case Study

The UK’s communications regulator, Ofcom, commissioned Winder.AI to produce a report to improve their understanding of the end-to-end processes that support the creation and deployment of automated content classifiers used in moderating online content.

Do you like DAGs? Implementing a Graph Executor for Bacalhau

Tue Jan 24, 2023, by Enrico Rotundo, in MLOps, Software Engineering, Talk, Case Study

Winder.AI helped Protocol Labs, a technology company in the crypto space, to help develop Bacalhau, a novel decentralised computational platform that focuses on the AI lifecycle. This case study describes some of our work to develop this project but for more information view the Bacalhau website.

Pachyderm ❤️ Spark ❤️ MLFlow - Scalable Machine Learning Provenance and Tracking

Tue Aug 23, 2022, by Enrico Rotundo, in Case Study, Mlops

This article shows how you can employ three frameworks to orchestrate a machine learning pipeline composed of an Extract, Transform, and Load step (ETL), and an ML training stage with comprehensive tracking of parameters, results and artifacts such as trained models. Furthermore, it shows how Pachyderm’s lineage integrates with an MLflow’s tracking server to provide artifact provenance.

Optimising Industrial Processes with Reinforcement Learning

Tue Aug 9, 2022, by Winder.AI, in Case Study, Reinforcement Learning

Winder.AI helped CMPC, a large paper milling company, to optimise their production process by using reinforcement learning. CMPC are now able to automate industrial processes that were previously manual. This case study describes our approach and the results.

Buildpacks - The Ultimate Machine Learning Container

Thu Jul 14, 2022, by Enrico Rotundo, Phil Winder, in Case Study, Mlops, Cloud-Native, Talk

Winder.AI worked with Grid.AI (now Lightning.ai) to investigate how Buildpacks can minimize the number of base containers required to run a modern platform. A summary of this work includes: Researching Buildpack best practices and adapting to modern machine learning workloads Reduce user burden and reduce maintenance costs by developing Buildpacks ready for production use Reporting and training on how Buildpacks can be leveraged in the future The video below presents this work.

A Comparison of Computational Frameworks: Spark, Dask, Snowflake, more

Fri Jun 24, 2022, by Enrico Rotundo, in MLOps, Case Study

Winder.AI worked with Protocol.AI to evaluate general-purpose computation frameworks. A summary of this work includes:

Comprehensive presentation evaluating the workflows and performance of each tool
A GitHub repository with benchmarks and sample applications
Documentation and summary video for Bacalhau documentation website

Save 80% of Your Machine Learning Training Bill on Kubernetes

Mon Jun 6, 2022, by Phil Winder, in Cloud Native, MLOps, Case Study

Winder.AI worked with Grid.AI to stress test managed Kubernetes services with the aim of reducing training time and cost. A summary of this work includes: Stress testing the scaling performance of the big three managed Kubernetes services Reducing the cost of training a 1000-node model by 80% The finding that some cloud vendors are better (cheaper) than others The Problem: How to Minimize the Time and Cost of Training Machine Learning Models Artificial intelligence (AI) workloads are resource hogs.

Using Reinforcement Learning to Attack Web Application Firewalls

Fri Sep 3, 2021, by Phil Winder, in Reinforcement Learning, Case Study

Introduction Ideally, the best way to improve the security of any system is to detect all vulnerabilities and patch them. Unfortunately this is rarely possible due to the extreme complexity of modern systems. One primary threat are payloads arriving from the public internet, with the attacker using them to discover and exploit vulnerabilities. For this reason, web application firewalls (WAF) are introduced to detect suspicious behaviour. These are often rules based and when they detect nefarious activities they significantly reduce the overall damage.