The Machine Learning Podcast: Recent Episodes
Tobias Macey
Detailed and technical explorations of machine learning and artificial intelligence with the researchers, engineers, and entrepreneurs who are shaping the industry
Summary Satellite imagery has given us a new perspective on our world, but it is limited by the field of view for the cameras. Synthetic Aperture Radar (SAR) allows for collecting images through clouds and in the dark, giving us a more consistent means of collecting data. In order to identify interesting details in such a vast amount of data it is necessary to use the power of machine learning. ICEYE has a fleet of satellites continuously collecting information about our planet. In this episode Tapio Friberg shares how they are applying ML to that data set to provide useful insights about fires, floods, and other terrestrial phenomena. Announcements Hello and welcome to the Machine Learning Podcast, the podcast about machine learning and how to bring it from idea to delivery. Your host is Tobias Macey and today I'm interviewing Tapio Friberg about building machine learning applications on top of SAR (Synthetic Aperture Radar) data to generate insights about our planet Interview Introduction How did you get involved in machine learning? Can you describe what ICEYE is and the story behind it? What are some of the applications of ML at ICEYE? What are some of the ways that SAR data poses a unique challenge to ML applications? What are some of the elements of the ML workflow that you are able to use "off the shelf" and where are the areas that you have had to build custom solutions? Can you share the structure of your engineering team and the role that the ML function plays in the larger organization? What does the end-to-end workflow for your ML model development and deployment look like? What are the operational requirements for your models? (e.g. batch execution, real-time, interactive inference, etc.) In the model definitions, what are the elements of the source domain that create the largest challenges? (e.g. noise from backscatter, variance in resolution, etc.) Once you have an output from an ML model how do you manage mapping between data domains to reflect insights from SAR sources onto a human understandable representation? Given that SAR data and earth imaging is still a very niche domain, how does that influence your ability to hire for open positions and the ways that you think about your contributions to the overall ML ecosystem? How can your work on using SAR as a representation of physical attributes help to improve capabilities in e.g. LIDAR, computer vision, etc.? What are the most interesting, innovative, or unexpected ways that you have seen ICEYE and SAR data used? What are the most interesting, unexpected, or challenging lessons that you have learned while working on ML for SAR data? What do you have planned for the future of ML applications at ICEYE? Contact Info LinkedIn (https://www.linkedin.com/in/tapio-friberg-319212235/) Parting Question From your perspective, what is the biggest barrier to adoption of machine learning today? Closing Announcements Thank you for listening! Don't forget to check out our other shows. The Data Engineering Podcast (https://www.dataengineeringpodcast.com) covers the latest on modern data management. Podcast.__init__ () covers the Python language, its community, and the innovative ways it is being used. Visit the site (https://www.themachinelearningpodcast.com) to subscribe to the show, sign up for the mailing list, and read the show notes. If you've learned something or tried out a project from the show then tell us about it! Email hosts@themachinelearningpodcast.com (mailto:hosts@themachinelearningpodcast.com)) with your story. To help other people find the show please leave a review on iTunes (https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243) and tell your friends and co-workers Links ICEYE (https://www.iceye.com/) SAR == Synthetic Aperture Radar (https://en.wikipedia.org/wiki/Synthetic-aperture_radar) Transfer Learning (https://en.wikipedia.org/wiki/Transfer_learning) The intro and outro music is from Hitman's Lovesong feat. Paola Graziano (https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/) by The Freak Fandango Orchestra (http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/)/CC BY-SA 3.0 (https://creativecommons.org/licenses/by-sa/3.0/)
SummaryBuilding a machine learning model one time can be done in an ad-hoc manner, but if you ever want to update it and serve it in production you need a way of repeating a complex sequence of operations. Dagster is an orchestration engine that understands the data that it is manipulating so that you can move beyond coarse task-based representations of your dependencies. In this episode Sandy Ryza explains how his background in machine learning has informed his work on the Dagster project and the foundational principles that it is built on to allow for collaboration across data engineering and machine learning concerns.InterviewIntroductionHow did you get involved in machine learning?Can you start by sharing a definition of "orchestration" in the context of machine learning projects?What is your assessment of the state of the orchestration ecosystem as it pertains to ML?modeling cycles and managing experiment iterations in the execution graphhow to balance flexibility with repeatability What are the most interesting, innovative, or unexpected ways that you have seen orchestration implemented/applied for machine learning?What are the most interesting, unexpected, or challenging lessons that you have learned while working on orchestration of ML workflows?When is Dagster the wrong choice?What do you have planned for the future of ML support in Dagster?Contact InfoLinkedIn (https://www.linkedin.com/in/sandyryza/)@s_ryz (https://twitter.com/s_ryz) on Twittersryza (https://github.com/sryza) on GitHubParting QuestionFrom your perspective, what is the biggest barrier to adoption of machine learning today?Closing AnnouncementsThank you for listening! Don't forget to check out our other shows. The Data Engineering Podcast (https://www.dataengineeringpodcast.com) covers the latest on modern data management. Podcast.__init__ () covers the Python language, its community, and the innovative ways it is being used.Visit the site (https://www.themachinelearningpodcast.com) to subscribe to the show, sign up for the mailing list, and read the show notes.If you've learned something or tried out a project from the show then tell us about it! Email hosts@themachinelearningpodcast.com (mailto:hosts@themachinelearningpodcast.com)) with your story.To help other people find the show please leave a review on iTunes (https://podcasts.apple.com/us/podcast/the-machine-learning-podcast/id1626358243) and tell your friends and co-workersLinksDagster (https://dagster.io/)Data Engineering Podcast Episode (https://www.dataengineeringpodcast.com/dagster-software-defined-assets-data-orchestration-episode-309/)Cloudera (https://www.cloudera.com/)Hadoop (https://hadoop.apache.org/)Apache Spark (https://spark.apache.org/)Peter Norvig (https://en.wikipedia.org/wiki/Peter_Norvig)Josh Wills (https://www.linkedin.com/in/josh-wills-13882b/)REPL == Read Eval Print Loop (https://en.wikipedia.org/wiki/Read%E2%80%93eval%E2%80%93print_loop)RStudio (https://posit.co/)Memoization (https://en.wikipedia.org/wiki/Memoization)MLFlow (https://mlflow.org/)Kedro (https://kedro.readthedocs.io/en/stable/)Data Engineering Podcast Episode (https://www.dataengineeringpodcast.com/kedro-data-pipeline-episode-100/)Metaflow (https://metaflow.org/)Podcast.__init__ Episode (https://www.pythonpodcast.com/metaflow-machine-learning-operations-episode-274/)Kubeflow (https://www.kubeflow.org/)dbt (https://www.getdbt.com/)Data Engineering Podcast Episode (https://www.dataengineeringpodcast.com/dbt-data-analytics-episode-81/)Airbyte (https://airbyte.com/)Data Engineering Podcast Episode (https://www.dataengineeringpodcast.com/airbyte-open-source-data-integration-episode-173/)The intro and outro music is from Hitman's Lovesong feat. Paola Graziano (https://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/Tales_Of_A_Dead_Fish/Hitmans_Lovesong/) by The Freak Fandango Orchestra (http://freemusicarchive.org/music/The_Freak_Fandango_Orchestra/)/CC BY-SA 3.0 (https://creativecommons.org/licenses/by-sa/3.0/)
Machine learning is a data-hungry approach to problem solving. Unfortunately, there are a number of problems that would benefit from the automation provided by artificial intelligence capabilities that don't come with troves of data to build from. Christopher Nguyen and his team at Aitomatic are working to address the "cold start" problem for ML by letting humans generate models by sharing their expertise through natural language. In this episode he explains how that works, the various ways that we can start to layer machine learning capabilities on top of each other, as well as the risks involved in doing so without incorporating lessons learned in the growth of the software industry.
Data is one of the core ingredients for machine learning, but the format in which it is understandable to humans is not a useful representation for models. Embedding vectors are a way to structure data in a way that is native to how models interpret and manipulate information. In this episode Frank Liu shares how the Towhee library simplifies the work of translating your unstructured data assets (e.g. images, audio, video, etc.) into embeddings that you can use efficiently for machine learning, and how it fits into your workflow for model development.
Because machine learning models are constantly interacting with inputs from the real world they are subject to a wide variety of failures. The most commonly discussed error condition is concept drift, but there are numerous other ways that things can go wrong. In this episode Wojtek Kuberski explains how NannyML is designed to compare the predicted performance of your model against its actual behavior to identify silent failures and provide context to allow you to determine whether and how urgently to address them.
Using machine learning in production requires a sophisticated set of cooperating technologies. A majority of resources that are available for understanding how to design and operate these platforms are focused on either simple examples that don't scale, or over-engineered technologies designed for the massive scale of big tech companies. In this episode Jacopo Tagliabue shares his vision for "ML at reasonable scale" and how you can adopt these patterns for building your own platforms.
The increasing sophistication of machine learning has enabled dramatic transformations of businesses and introduced new product categories. At Assembly AI they are offering advanced speech recognition and natural language models as an API service. In this episode founder Dylan Fox discusses the unique challenges of building a business with machine learning as the core product.
The majority of machine learning projects that you read about or work on are built around batch processes. The model is trained, and then validated, and then deployed, with each step being a discrete and isolated task. Unfortunately, the real world is rarely static, leading to concept drift and model failures. River is a framework for building streaming machine learning projects that can constantly adapt to new information. In this episode Max Halford explains how the project works, why you might (or might not) want to consider streaming ML, and how to get started building with River.
Machine learning is a transformative tool for the organizations that can take advantage of it. While the frameworks and platforms for building machine learning applications are becoming more powerful and broadly available, there is still a significant investment of time, money, and talent required to take full advantage of it. In order to reduce that barrier further Adam Oliner and Brian Calvert, along with their other co-founders, started Graft. In this episode Adam and Brian explain how they have built a platform designed to empower everyone in the business to take part in designing and building ML projects, while managing the end-to-end workflow required to go from data to production.
In order for a machine learning model to build connections and context across the data that is fed into it the raw data needs to be engineered into semantic features. This is a process that can be tedious and full of toil, requiring constant upkeep and often leading to rework across projects and teams. In order to reduce the amount of wasted effort and speed up experimentation and training iterations a new generation of services are being developed. Tecton first built a feature store to serve as a central repository of engineered features and keep them up to date for training and inference. Since then they have expanded the set of tools and services to be a full-fledged feature platform. In this episode Kevin Stumpf explains the different capabilities and activities related to features that are necessary to maintain velocity in your machine learning projects.
Machine learning is a data hungry activity, and the quality of the resulting model is highly dependent on the quality of the inputs that it receives. Generating sufficient quantities of high quality labeled data is an expensive and time consuming process. In order to reduce that time and cost Alex Ratner and his team at Snorkel AI have built a system for powering data-centric machine learning development. In this episode he explains how the Snorkel platform allows domain experts to create labeling functions that translate their expertise into reusable logic that dramatically reduces the time needed to build training data sets and drives down the total cost.
Deep learning is a revolutionary category of machine learning that accelerates our ability to build powerful inference models. Along with that power comes a great deal of complexity in determining what neural architectures are best suited to a given task, engineering features, scaling computation, etc. Predibase is building on the successes of the Ludwig framework for declarative deep learning and Horovod for horizontally distributing model training. In this episode CTO and co-founder of Predibase, Travis Addair, explains how they are reducing the burden of model development even further with their managed service for declarative and low-code ML and how they are integrating with the growing ecosystem of solutions for the full ML lifecycle.
Machine learning is a force multiplier that can generate an outsized impact on your organization. Unfortunately, if you are feeding your ML model garbage data, then you will get orders of magnitude more garbage out of it. The team behind Galileo experienced that pain for themselves and have set out to make data management and cleaning for machine learning a first class concern in your workflow. In this episode Vikram Chatterji shares the story of how Galileo got started and how you can use their platform to fix your ML data so that you can get back to the fun parts.
Machine learning has the potential to transform industries and revolutionize business capabilities, but only if the models are reliable and robust. Because of the fundamental probabilistic nature of machine learning techniques it can be challenging to test and validate the generated models. The team at Deepchecks understands the widespread need to easily and repeatably check and verify the outputs of machine learning models and the complexity involved in making it a reality. In this episode Shir Chorev and Philip Tannor explain how they are addressing the problem with their open source deepchecks library and how you can start using it today to build trust in your machine learning applications.
Building an ML model is getting easier than ever, but it is still a challenge to get that model in front of the people that you built it for. Baseten is a platform that helps you quickly generate a full stack application powered by your model. You can easily create a web interface and APIs powered by the model you created, or a pre-trained model from their library. In this episode Tuhin Srivastava, co-founder of Basten, explains how the platform empowers data scientists and ML engineers to get their work in production without having to negotiate for help from their application development colleagues.
Machine learning and AI are the biggest catalysts for change and innovation in the modern era. Tune in to the Machine Learning Podcast to stay up to date with this rapidly evolving industry.