Elixir Wizards is an interview-format podcast, focused on engineers who use the Elixir programming language. Initially launched in early 2019, each season focuses on a specific topic or topics, with each interview focusing on the guest's experience and opinions on the topic. Elixir Wizards is hosted by Eric Oestrich and Sundi Myint of SmartLogic, a dev shop that’s been building custom software since 2005 and running Elixir applications in production since 2015. Learn more about how SmartLogic uses Phoenix and Elixir. (https://smartlogic.io/phoenix-and-elixir?utm_source=podcast)
Sean Moriarity on the Future of Machine Learning with Elixir
Sean Moriarity, author of Genetic Algorithms in Elixir and creator of the Axon Library, joins Elixir Wizards Sundi Myint and Bilal Hankins to discuss Elixir’s role in the future of machine learning and AI. He explains the difference between artificial intelligence, chat models, machine learning, deep learning systems, and neural networks.
Large language models have great potential for code generation, education tools, streamlining workflow, and more. Deployment, development experience, and real-time processing make Elixir an ideal programming language for creating and improving machine learning tools.
Key Topics Discussed in this Episode:
- The difference between machine learning and artificial intelligence
- How Axon builds on top of the Nx library for deep learning in Elixir
- Why logic cannot fully define characteristics that identify golden retrievers
- How Google Translate uses machine learning with a unified language model
- The difficulties in translating concepts with no direct counterpart between languages
- Data cleaning and labeling challenges
- How Sean's interest in sports betting led to exploring machine learning
- Why Sean's NBA betting model recommended betting $0 to maximize profit
- Getting started with machine learning and Elixir projects
- Attention mechanisms in neural networks
- Bias and exceptions in machine translation models
- How hummus preference was used to determine Sundi's Hogwarts house
- Sean's work on a LiveView interface for ChatGPT
- Why Elixir's deployment story, development experience, and real-time processing are good fits for machine learning applications
Links Mentioned:
Genetic Algorithms in Elixir by Sean Moriarity: https://pragprog.com/titles/smgaelixir/genetic-algorithms-in-elixir/
Axon Deep Learning in Elixir: https://seanmoriarity.com/2021/04/08/axon-deep-learning-in-elixir/
Nx Axon: https://github.com/elixir-nx/axon
Sean’s Twitter: https://twitter.com/sean_moriarity
Weston the Golden’s IG: https://www.instagram.com/westonthegolden_/
Sean’s Github: https://github.com/seanmor5
Bumblebee: https://github.com/elixir-nx/bumblebee
Sal Khan’s TedTalk about AI in Education: https://www.ted.com/talks/sal_khan_how_ai_could_save_not_destroy_education/c
Publicly Available Datasets/Intro to Machine Learning: https://www.kaggle.com/
Use code WIZARD for $100 off your ticket to Empex NYC in Brooklyn, NY on June 9, 2023 https://ti.to/empex-ny/empex-nyc-2023
Special Guest: Sean Moriarity.